From ec6282a82962a12c176aff7b8a0df6714c152105 Mon Sep 17 00:00:00 2001 From: RandomDefaultUser Date: Sun, 12 May 2024 08:55:18 +0000 Subject: [PATCH] deploy: 7abd9d7b4c98a73f4ab71d4b2b968d1de5325d21 --- _modules/mala/common/check_modules.html | 4 - _modules/mala/common/parallelizer.html | 48 ++-- _modules/mala/common/parameters.html | 113 +++++----- _modules/mala/datahandling/data_handler.html | 19 +- .../mala/datahandling/data_handler_base.html | 2 +- _modules/mala/datahandling/data_scaler.html | 21 +- .../mala/datahandling/lazy_load_dataset.html | 27 ++- .../lazy_load_dataset_single.html | 8 +- _modules/mala/network/network.html | 15 +- _modules/mala/network/objective_naswot.html | 2 +- _modules/mala/network/runner.html | 134 ++++++----- _modules/mala/network/trainer.html | 210 +++++++++++------- _sources/advanced_usage/trainingmodel.rst.txt | 65 ++++++ advanced_usage/trainingmodel.html | 61 +++++ api/mala.common.parallelizer.html | 14 +- api/mala.common.parameters.html | 30 +-- api/mala.datahandling.data_scaler.html | 4 +- api/mala.datahandling.lazy_load_dataset.html | 2 +- ...datahandling.lazy_load_dataset_single.html | 2 +- api/mala.network.runner.html | 12 +- genindex.html | 6 +- objects.inv | Bin 6523 -> 6510 bytes searchindex.js | 2 +- 23 files changed, 496 insertions(+), 305 deletions(-) diff --git a/_modules/mala/common/check_modules.html b/_modules/mala/common/check_modules.html index e8d219da7..89f7f7635 100644 --- a/_modules/mala/common/check_modules.html +++ b/_modules/mala/common/check_modules.html @@ -87,10 +87,6 @@

Source code for mala.common.check_modules

             "available": False,
             "description": "Enables inference parallelization.",
         },
-        "horovod": {
-            "available": False,
-            "description": "Enables training parallelization.",
-        },
         "lammps": {
             "available": False,
             "description": "Enables descriptor calculation for data preprocessing "
diff --git a/_modules/mala/common/parallelizer.html b/_modules/mala/common/parallelizer.html
index f2cafdcb4..0fe12a441 100644
--- a/_modules/mala/common/parallelizer.html
+++ b/_modules/mala/common/parallelizer.html
@@ -78,15 +78,13 @@ 
Source code for mala.common.parallelizer
 
 from collections import defaultdict
 import platform
+import os
 import warnings
 
-try:
-    import horovod.torch as hvd
-except ModuleNotFoundError:
-    pass
 import torch
+import torch.distributed as dist
 
-use_horovod = False
+use_ddp = False
 use_mpi = False
 comm = None
 local_mpi_rank = None
@@ -109,45 +107,43 @@ 
Source code for mala.common.parallelizer
     current_verbosity = new_value

 
 
-
[docs]def set_horovod_status(new_value):
+
[docs]def set_ddp_status(new_value):
     """
-    Set the horovod status.
+    Set the ddp status.
 
-    By setting the horovod status via this function it can be ensured that
+    By setting the ddp status via this function it can be ensured that
     printing works in parallel. The Parameters class does that for the user.
 
     Parameters
     ----------
     new_value : bool
-        Value the horovod status has.
+        Value the ddp status has.
 
     """
     if use_mpi is True and new_value is True:
         raise Exception(
-            "Cannot use horovod and inference-level MPI at "
-            "the same time yet."
+            "Cannot use ddp and inference-level MPI at " "the same time yet."
         )
-    global use_horovod
-    use_horovod = new_value

+    global use_ddp
+    use_ddp = new_value

 
 
 
[docs]def set_mpi_status(new_value):
     """
     Set the MPI status.
 
-    By setting the horovod status via this function it can be ensured that
+    By setting the MPI status via this function it can be ensured that
     printing works in parallel. The Parameters class does that for the user.
 
     Parameters
     ----------
     new_value : bool
-        Value the horovod status has.
+        Value the MPI status has.
 
     """
-    if use_horovod is True and new_value is True:
+    if use_ddp is True and new_value is True:
         raise Exception(
-            "Cannot use horovod and inference-level MPI at "
-            "the same time yet."
+            "Cannot use ddp and inference-level MPI at " "the same time yet."
         )
     global use_mpi
     use_mpi = new_value
@@ -195,8 +191,8 @@ 
Source code for mala.common.parallelizer
         The rank of the current thread.
 
     """
-    if use_horovod:
-        return hvd.rank()
+    if use_ddp:
+        return dist.get_rank()
     if use_mpi:
         return comm.Get_rank()
     return 0

@@ -235,8 +231,8 @@ 
Source code for mala.common.parallelizer
     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
     DEALINGS IN THE SOFTWARE.
     """
-    if use_horovod:
-        return hvd.local_rank()
+    if use_ddp:
+        return int(os.environ.get("LOCAL_RANK"))
     if use_mpi:
         global local_mpi_rank
         if local_mpi_rank is None:
@@ -263,8 +259,8 @@ 
Source code for mala.common.parallelizer
     size : int
         The number of ranks.
     """
-    if use_horovod:
-        return hvd.size()
+    if use_ddp:
+        return dist.get_world_size()
     if use_mpi:
         return comm.Get_size()

 
@@ -285,8 +281,8 @@ 
Source code for mala.common.parallelizer
 
 
[docs]def barrier():
     """General interface for a barrier."""
-    if use_horovod:
-        hvd.allreduce(torch.tensor(0), name="barrier")
+    if use_ddp:
+        dist.barrier()
     if use_mpi:
         comm.Barrier()
     return

diff --git a/_modules/mala/common/parameters.html b/_modules/mala/common/parameters.html
index 665e2c379..84bfa6046 100644
--- a/_modules/mala/common/parameters.html
+++ b/_modules/mala/common/parameters.html
@@ -83,19 +83,13 @@ 
Source code for mala.common.parameters
 import pickle
 from time import sleep
 
-horovod_available = False
-try:
-    import horovod.torch as hvd
-
-    horovod_available = True
-except ModuleNotFoundError:
-    pass
 import numpy as np
 import torch
+import torch.distributed as dist
 
 from mala.common.parallelizer import (
     printout,
-    set_horovod_status,
+    set_ddp_status,
     set_mpi_status,
     get_rank,
     get_local_rank,
@@ -116,7 +110,7 @@ 
Source code for mala.common.parameters
         super(ParametersBase, self).__init__()
         self._configuration = {
             "gpu": False,
-            "horovod": False,
+            "ddp": False,
             "mpi": False,
             "device": "cpu",
             "openpmd_configuration": {},
@@ -152,8 +146,8 @@ 
Source code for mala.common.parameters
     def _update_gpu(self, new_gpu):
         self._configuration["gpu"] = new_gpu
 
-    def _update_horovod(self, new_horovod):
-        self._configuration["horovod"] = new_horovod
+    def _update_ddp(self, new_ddp):
+        self._configuration["ddp"] = new_ddp
 
     def _update_mpi(self, new_mpi):
         self._configuration["mpi"] = new_mpi
@@ -762,10 +756,6 @@ 
Source code for mala.common.parameters
         validation loss has to plateau before the schedule takes effect).
         Default: 0.
 
-    use_compression : bool
-        If True and horovod is used, horovod compression will be used for
-        allreduce communication. This can improve performance.
-
     num_workers : int
         Number of workers to be used for data loading.
 
@@ -826,7 +816,6 @@ 
Source code for mala.common.parameters
         self.learning_rate_scheduler = None
         self.learning_rate_decay = 0.1
         self.learning_rate_patience = 0
-        self.use_compression = False
         self.num_workers = 0
         self.use_shuffling_for_samplers = True
         self.checkpoints_each_epoch = 0
@@ -842,8 +831,8 @@ 
Source code for mala.common.parameters
         self.training_report_frequency = 1000
         self.profiler_range = None  # [1000, 2000]
 
-    def _update_horovod(self, new_horovod):
-        super(ParametersRunning, self)._update_horovod(new_horovod)
+    def _update_ddp(self, new_ddp):
+        super(ParametersRunning, self)._update_ddp(new_ddp)
         self.during_training_metric = self.during_training_metric
         self.after_before_training_metric = self.after_before_training_metric
 
@@ -865,10 +854,10 @@ 
Source code for mala.common.parameters
     @during_training_metric.setter
     def during_training_metric(self, value):
         if value != "ldos":
-            if self._configuration["horovod"]:
+            if self._configuration["ddp"]:
                 raise Exception(
                     "Currently, MALA can only operate with the "
-                    '"ldos" metric for horovod runs.'
+                    '"ldos" metric for ddp runs.'
                 )
         self._during_training_metric = value
 
@@ -890,20 +879,20 @@ 
Source code for mala.common.parameters
     @after_before_training_metric.setter
     def after_before_training_metric(self, value):
         if value != "ldos":
-            if self._configuration["horovod"]:
+            if self._configuration["ddp"]:
                 raise Exception(
                     "Currently, MALA can only operate with the "
-                    '"ldos" metric for horovod runs.'
+                    '"ldos" metric for ddp runs.'
                 )
         self._after_before_training_metric = value
 
     @during_training_metric.setter
     def during_training_metric(self, value):
         if value != "ldos":
-            if self._configuration["horovod"]:
+            if self._configuration["ddp"]:
                 raise Exception(
                     "Currently, MALA can only operate with the "
-                    '"ldos" metric for horovod runs.'
+                    '"ldos" metric for ddp runs.'
                 )
         self._during_training_metric = value
 
@@ -1294,7 +1283,7 @@ 
Source code for mala.common.parameters
 
         # Properties
         self.use_gpu = False
-        self.use_horovod = False
+        self.use_ddp = False
         self.use_mpi = False
         self.verbosity = 1
         self.device = "cpu"
@@ -1380,32 +1369,36 @@ 
Source code for mala.common.parameters
         self.hyperparameters._update_gpu(self.use_gpu)
 
     @property
-    def use_horovod(self):
-        """Control whether or not horovod is used for parallel training."""
-        return self._use_horovod
-
-    @use_horovod.setter
-    def use_horovod(self, value):
-        if value is False:
-            self._use_horovod = False
-        else:
-            if horovod_available:
-                hvd.init()
-                # Invalidate, will be updated in setter.
-                set_horovod_status(value)
-                self.device = None
-                self._use_horovod = value
-                self.network._update_horovod(self.use_horovod)
-                self.descriptors._update_horovod(self.use_horovod)
-                self.targets._update_horovod(self.use_horovod)
-                self.data._update_horovod(self.use_horovod)
-                self.running._update_horovod(self.use_horovod)
-                self.hyperparameters._update_horovod(self.use_horovod)
-            else:
-                parallel_warn(
-                    "Horovod requested, but not installed found. "
-                    "MALA will operate without horovod only."
-                )
+    def use_ddp(self):
+        """Control whether or not dd is used for parallel training."""
+        return self._use_ddp
+
+    @use_ddp.setter
+    def use_ddp(self, value):
+        if value:
+            if self.verbosity > 1:
+                print("Initializing torch.distributed.")
+            # JOSHR:
+            # We start up torch distributed here. As is fairly standard
+            # convention, we get the rank and world size arguments via
+            # environment variables (RANK, WORLD_SIZE). In addition to
+            # those variables, LOCAL_RANK, MASTER_ADDR and MASTER_PORT
+            # should be set.
+            rank = int(os.environ.get("RANK"))
+            world_size = int(os.environ.get("WORLD_SIZE"))
+
+            dist.init_process_group("nccl", rank=rank, world_size=world_size)
+
+        set_ddp_status(value)
+        # Invalidate, will be updated in setter.
+        self.device = None
+        self._use_ddp = value
+        self.network._update_ddp(self.use_ddp)
+        self.descriptors._update_ddp(self.use_ddp)
+        self.targets._update_ddp(self.use_ddp)
+        self.data._update_ddp(self.use_ddp)
+        self.running._update_ddp(self.use_ddp)
+        self.hyperparameters._update_ddp(self.use_ddp)
 
     @property
     def device(self):
@@ -1428,7 +1421,7 @@ 
Source code for mala.common.parameters
 
     @property
     def use_mpi(self):
-        """Control whether or not horovod is used for parallel training."""
+        """Control whether or not MPI is used for paralle inference."""
         return self._use_mpi
 
     @use_mpi.setter
@@ -1627,7 +1620,9 @@ 
Source code for mala.common.parameters
         self.hyperparameters._update_device(device_temp)

 
 
[docs]    @classmethod
-    def load_from_file(cls, file, save_format="json", no_snapshots=False):
+    def load_from_file(
+        cls, file, save_format="json", no_snapshots=False, force_no_ddp=False
+    ):
         """
         Load a Parameters object from a file.
 
@@ -1682,7 +1677,10 @@ 
Source code for mala.common.parameters
                     not isinstance(json_dict[key], dict)
                     or key == "openpmd_configuration"
                 ):
-                    setattr(loaded_parameters, key, json_dict[key])
+                    if key == "use_ddp" and force_no_ddp is True:
+                        setattr(loaded_parameters, key, False)
+                    else:
+                        setattr(loaded_parameters, key, json_dict[key])
             if no_snapshots is True:
                 loaded_parameters.data.snapshot_directories_list = []
         else:
@@ -1715,7 +1713,7 @@ 
Source code for mala.common.parameters
         )

 
 
[docs]    @classmethod
-    def load_from_json(cls, file, no_snapshots=False):
+    def load_from_json(cls, file, no_snapshots=False, force_no_ddp=False):
         """
         Load a Parameters object from a json file.
 
@@ -1735,7 +1733,10 @@ 
Source code for mala.common.parameters
 
         """
         return Parameters.load_from_file(
-            file, save_format="json", no_snapshots=no_snapshots
+            file,
+            save_format="json",
+            no_snapshots=no_snapshots,
+            force_no_ddp=force_no_ddp,
         )

 

 
diff --git a/_modules/mala/datahandling/data_handler.html b/_modules/mala/datahandling/data_handler.html
index 1c02e9c93..79f58a46d 100644
--- a/_modules/mala/datahandling/data_handler.html
+++ b/_modules/mala/datahandling/data_handler.html
@@ -148,14 +148,14 @@ 
Source code for mala.datahandling.data_handler
if self.input_data_scaler is None:
             self.input_data_scaler = DataScaler(
                 self.parameters.input_rescaling_type,
-                use_horovod=self.use_horovod,
+                use_ddp=self.use_ddp,
             )
 
         self.output_data_scaler = output_data_scaler
         if self.output_data_scaler is None:
             self.output_data_scaler = DataScaler(
                 self.parameters.output_rescaling_type,
-                use_horovod=self.use_horovod,
+                use_ddp=self.use_ddp,
             )
 
         # Actual data points in the different categories.
@@ -715,7 +715,8 @@ 
Source code for mala.datahandling.data_handler
self.output_data_scaler,
                     self.descriptor_calculator,
                     self.target_calculator,
-                    self.use_horovod,
+                    self.use_ddp,
+                    self.parameters._configuration["device"],
                 )
             )
             self.validation_data_sets.append(
@@ -726,7 +727,8 @@ 
Source code for mala.datahandling.data_handler
self.output_data_scaler,
                     self.descriptor_calculator,
                     self.target_calculator,
-                    self.use_horovod,
+                    self.use_ddp,
+                    self.parameters._configuration["device"],
                 )
             )
 
@@ -739,7 +741,8 @@ 
Source code for mala.datahandling.data_handler
self.output_data_scaler,
                         self.descriptor_calculator,
                         self.target_calculator,
-                        self.use_horovod,
+                        self.use_ddp,
+                        self.parameters._configuration["device"],
                         input_requires_grad=True,
                     )
                 )
@@ -782,7 +785,7 @@ 
Source code for mala.datahandling.data_handler
self.output_data_scaler,
                             self.descriptor_calculator,
                             self.target_calculator,
-                            self.use_horovod,
+                            self.use_ddp,
                         )
                     )
                 if snapshot.snapshot_function == "va":
@@ -796,7 +799,7 @@ 
Source code for mala.datahandling.data_handler
self.output_data_scaler,
                             self.descriptor_calculator,
                             self.target_calculator,
-                            self.use_horovod,
+                            self.use_ddp,
                         )
                     )
                 if snapshot.snapshot_function == "te":
@@ -810,7 +813,7 @@ 
Source code for mala.datahandling.data_handler
self.output_data_scaler,
                             self.descriptor_calculator,
                             self.target_calculator,
-                            self.use_horovod,
+                            self.use_ddp,
                             input_requires_grad=True,
                         )
                     )
diff --git a/_modules/mala/datahandling/data_handler_base.html b/_modules/mala/datahandling/data_handler_base.html
index 78641f5c2..01d2a70bb 100644
--- a/_modules/mala/datahandling/data_handler_base.html
+++ b/_modules/mala/datahandling/data_handler_base.html
@@ -113,7 +113,7 @@ 
Source code for mala.datahandling.data_handler_base
descriptor_calculator=None,
     ):
         self.parameters: ParametersData = parameters.data
-        self.use_horovod = parameters.use_horovod
+        self.use_ddp = parameters.use_ddp
 
         # Calculators used to parse data from compatible files.
         self.target_calculator = target_calculator
diff --git a/_modules/mala/datahandling/data_scaler.html b/_modules/mala/datahandling/data_scaler.html
index 424520e4c..3bfb7b3fc 100644
--- a/_modules/mala/datahandling/data_scaler.html
+++ b/_modules/mala/datahandling/data_scaler.html
@@ -77,14 +77,9 @@ 
Source code for mala.datahandling.data_scaler
"""DataScaler class for scaling DFT data."""
 
 import pickle
-
-try:
-    import horovod.torch as hvd
-except ModuleNotFoundError:
-    # Warning is thrown by parameters class
-    pass
 import numpy as np
 import torch
+import torch.distributed as dist
 
 from mala.common.parameters import printout
 
@@ -110,13 +105,13 @@ 
Source code for mala.datahandling.data_scaler
        - "feature-wise-normal": Row Min-Max scaling (Scale to be in range
           0...1)
 
-    use_horovod : bool
-        If True, the DataScaler will use horovod to check that data is
+    use_ddp : bool
+        If True, the DataScaler will use ddp to check that data is
         only saved on the root process in parallel execution.
     """
 
-    def __init__(self, typestring, use_horovod=False):
-        self.use_horovod = use_horovod
+    def __init__(self, typestring, use_ddp=False):
+        self.use_ddp = use_ddp
         self.typestring = typestring
         self.scale_standard = False
         self.scale_normal = False
@@ -485,9 +480,9 @@ 
Source code for mala.datahandling.data_scaler
        save_format :
             File format which will be used for saving.
         """
-        # If we use horovod, only save the network on root.
-        if self.use_horovod:
-            if hvd.rank() != 0:
+        # If we use ddp, only save the network on root.
+        if self.use_ddp:
+            if dist.get_rank() != 0:
                 return
         if save_format == "pickle":
             with open(filename, "wb") as handle:
diff --git a/_modules/mala/datahandling/lazy_load_dataset.html b/_modules/mala/datahandling/lazy_load_dataset.html
index a8c914b21..41d287a36 100644
--- a/_modules/mala/datahandling/lazy_load_dataset.html
+++ b/_modules/mala/datahandling/lazy_load_dataset.html
@@ -78,13 +78,9 @@ 
Source code for mala.datahandling.lazy_load_dataset
import os
 
-try:
-    import horovod.torch as hvd
-except ModuleNotFoundError:
-    # Warning is thrown by Parameters class.
-    pass
 import numpy as np
 import torch
+import torch.distributed as dist
 from torch.utils.data import Dataset
 
 from mala.common.parallelizer import barrier
@@ -123,8 +119,8 @@ 
Source code for mala.datahandling.lazy_load_dataset
    target_calculator : mala.targets.target.Target or derivative
         Used to do unit conversion on output data.
 
-    use_horovod : bool
-        If true, it is assumed that horovod is used.
+    use_ddp : bool
+        If true, it is assumed that ddp is used.
 
     input_requires_grad : bool
         If True, then the gradient is stored for the inputs.
@@ -138,7 +134,8 @@ 
Source code for mala.datahandling.lazy_load_dataset
output_data_scaler,
         descriptor_calculator,
         target_calculator,
-        use_horovod,
+        use_ddp,
+        device,
         input_requires_grad=False,
     ):
         self.snapshot_list = []
@@ -156,9 +153,10 @@ 
Source code for mala.datahandling.lazy_load_dataset
self.currently_loaded_file = None
         self.input_data = np.empty(0)
         self.output_data = np.empty(0)
-        self.use_horovod = use_horovod
+        self.use_ddp = use_ddp
         self.return_outputs_directly = False
         self.input_requires_grad = input_requires_grad
+        self.device = device
 
     @property
     def return_outputs_directly(self):
@@ -198,9 +196,14 @@ 
Source code for mala.datahandling.lazy_load_dataset
        """
         used_perm = torch.randperm(self.number_of_snapshots)
         barrier()
-        if self.use_horovod:
-            used_perm = hvd.broadcast(used_perm, 0)
-        self.snapshot_list = [self.snapshot_list[i] for i in used_perm]
+        if self.use_ddp:
+            used_perm = used_perm.to(device=self.device)
+            dist.broadcast(used_perm, 0)
+            self.snapshot_list = [
+                self.snapshot_list[i] for i in used_perm.to("cpu")
+            ]
+        else:
+            self.snapshot_list = [self.snapshot_list[i] for i in used_perm]
         self.get_new_data(0)

 
 
[docs]    def get_new_data(self, file_index):
diff --git a/_modules/mala/datahandling/lazy_load_dataset_single.html b/_modules/mala/datahandling/lazy_load_dataset_single.html
index 88eab43e0..85e18f6c8 100644
--- a/_modules/mala/datahandling/lazy_load_dataset_single.html
+++ b/_modules/mala/datahandling/lazy_load_dataset_single.html
@@ -115,8 +115,8 @@ 
Source code for mala.datahandling.lazy_load_dataset_single
    target_calculator : mala.targets.target.Target or derivative
         Used to do unit conversion on output data.
 
-    use_horovod : bool
-        If true, it is assumed that horovod is used.
+    use_ddp : bool
+        If true, it is assumed that ddp is used.
 
     input_requires_grad : bool
         If True, then the gradient is stored for the inputs.
@@ -132,7 +132,7 @@ 
Source code for mala.datahandling.lazy_load_dataset_single
output_data_scaler,
         descriptor_calculator,
         target_calculator,
-        use_horovod,
+        use_ddp,
         input_requires_grad=False,
     ):
         self.snapshot = snapshot
@@ -150,7 +150,7 @@ 
Source code for mala.datahandling.lazy_load_dataset_single
self.currently_loaded_file = None
         self.input_data = np.empty(0)
         self.output_data = np.empty(0)
-        self.use_horovod = use_horovod
+        self.use_ddp = use_ddp
         self.return_outputs_directly = False
         self.input_requires_grad = input_requires_grad
 
diff --git a/_modules/mala/network/network.html b/_modules/mala/network/network.html
index c1876b086..2b459611b 100644
--- a/_modules/mala/network/network.html
+++ b/_modules/mala/network/network.html
@@ -79,18 +79,13 @@ 
Source code for mala.network.network
 from abc import abstractmethod
 import numpy as np
 import torch
+import torch.distributed as dist
 import torch.nn as nn
 import torch.nn.functional as functional
 
 from mala.common.parameters import Parameters
 from mala.common.parallelizer import printout
 
-try:
-    import horovod.torch as hvd
-except ModuleNotFoundError:
-    # Warning is thrown by parameters class
-    pass
-
 
 
[docs]class Network(nn.Module):
     """
@@ -145,7 +140,7 @@ 
Source code for mala.network.network
 
     def __init__(self, params: Parameters):
         # copy the network params from the input parameter object
-        self.use_horovod = params.use_horovod
+        self.use_ddp = params.use_ddp
         self.mini_batch_size = params.running.mini_batch_size
         self.params = params.network
 
@@ -238,9 +233,9 @@ 
Source code for mala.network.network
         path_to_file : string
             Path to the file in which the network should be saved.
         """
-        # If we use horovod, only save the network on root.
-        if self.use_horovod:
-            if hvd.rank() != 0:
+        # If we use ddp, only save the network on root.
+        if self.use_ddp:
+            if dist.get_rank() != 0:
                 return
         torch.save(
             self.state_dict(),
diff --git a/_modules/mala/network/objective_naswot.html b/_modules/mala/network/objective_naswot.html
index c71a60dbc..fd3c2fd99 100644
--- a/_modules/mala/network/objective_naswot.html
+++ b/_modules/mala/network/objective_naswot.html
@@ -152,7 +152,7 @@ 
Source code for mala.network.objective_naswot
do_shuffle = self.params.running.use_shuffling_for_samplers
             if (
                 self.data_handler.parameters.use_lazy_loading
-                or self.params.use_horovod
+                or self.params.use_ddp
             ):
                 do_shuffle = False
             if self.params.running.use_shuffling_for_samplers:
diff --git a/_modules/mala/network/runner.html b/_modules/mala/network/runner.html
index 9cb8f58cc..748bab983 100644
--- a/_modules/mala/network/runner.html
+++ b/_modules/mala/network/runner.html
@@ -79,14 +79,12 @@ 
Source code for mala.network.runner
 import os
 from zipfile import ZipFile, ZIP_STORED
 
-try:
-    import horovod.torch as hvd
-except ModuleNotFoundError:
-    # Warning is thrown by Parameters class
-    pass
 import numpy as np
 import torch
+import torch.distributed as dist
 
+import mala
+from mala.common.parallelizer import get_rank
 from mala.common.parameters import ParametersRunning
 from mala.network.network import Network
 from mala.datahandling.data_scaler import DataScaler
@@ -156,50 +154,62 @@ 
Source code for mala.network.runner
             data is already present in the DataHandler object, it can be saved
             by setting.
         """
-        model_file = run_name + ".network.pth"
-        iscaler_file = run_name + ".iscaler.pkl"
-        oscaler_file = run_name + ".oscaler.pkl"
-        params_file = run_name + ".params.json"
-        if save_runner:
-            optimizer_file = run_name + ".optimizer.pth"
-
-        self.parameters_full.save(os.path.join(save_path, params_file))
-        self.network.save_network(os.path.join(save_path, model_file))
-        self.data.input_data_scaler.save(os.path.join(save_path, iscaler_file))
-        self.data.output_data_scaler.save(
-            os.path.join(save_path, oscaler_file)
-        )
+        # If a model is trained via DDP, we need to make sure saving is only
+        # performed on rank 0.
+        if get_rank() == 0:
+            model_file = run_name + ".network.pth"
+            iscaler_file = run_name + ".iscaler.pkl"
+            oscaler_file = run_name + ".oscaler.pkl"
+            params_file = run_name + ".params.json"
+            if save_runner:
+                optimizer_file = run_name + ".optimizer.pth"
+
+            self.parameters_full.save(os.path.join(save_path, params_file))
+            if self.parameters_full.use_ddp:
+                self.network.module.save_network(
+                    os.path.join(save_path, model_file)
+                )
+            else:
+                self.network.save_network(os.path.join(save_path, model_file))
+            self.data.input_data_scaler.save(
+                os.path.join(save_path, iscaler_file)
+            )
+            self.data.output_data_scaler.save(
+                os.path.join(save_path, oscaler_file)
+            )
 
-        files = [model_file, iscaler_file, oscaler_file, params_file]
-        if save_runner:
-            files += [optimizer_file]
-        if zip_run:
-            if additional_calculation_data is not None:
-                additional_calculation_file = run_name + ".info.json"
-                if isinstance(additional_calculation_data, str):
-                    self.data.target_calculator.read_additional_calculation_data(
-                        additional_calculation_data
-                    )
-                    self.data.target_calculator.write_additional_calculation_data(
-                        os.path.join(save_path, additional_calculation_file)
-                    )
-                elif isinstance(additional_calculation_data, bool):
-                    if additional_calculation_data:
+            files = [model_file, iscaler_file, oscaler_file, params_file]
+            if save_runner:
+                files += [optimizer_file]
+            if zip_run:
+                if additional_calculation_data is not None:
+                    additional_calculation_file = run_name + ".info.json"
+                    if isinstance(additional_calculation_data, str):
+                        self.data.target_calculator.read_additional_calculation_data(
+                            additional_calculation_data
+                        )
                         self.data.target_calculator.write_additional_calculation_data(
                             os.path.join(
                                 save_path, additional_calculation_file
                             )
                         )
+                    elif isinstance(additional_calculation_data, bool):
+                        if additional_calculation_data:
+                            self.data.target_calculator.write_additional_calculation_data(
+                                os.path.join(
+                                    save_path, additional_calculation_file
+                                )
+                            )
 
-                files.append(additional_calculation_file)
-            with ZipFile(
-                os.path.join(save_path, run_name + ".zip"),
-                "w",
-                compression=ZIP_STORED,
-            ) as zip_obj:
-                for file in files:
-                    zip_obj.write(os.path.join(save_path, file), file)
-                    os.remove(os.path.join(save_path, file))

+                    files.append(additional_calculation_file)
+                with ZipFile(
+                    os.path.join(save_path, run_name + ".zip"),
+                    "w",
+                    compression=ZIP_STORED,
+                ) as zip_obj:
+                    for file in files:
+                        zip_obj.write(os.path.join(save_path, file), file)
+                        os.remove(os.path.join(save_path, file))

 
 
[docs]    @classmethod
     def load_run(
@@ -212,6 +222,7 @@ 
Source code for mala.network.runner
         prepare_data=False,
         load_with_mpi=None,
         load_with_gpu=None,
+        load_with_ddp=None,
     ):
         """
         Load a run.
@@ -239,7 +250,7 @@ 
Source code for mala.network.runner
             If True, the data will be loaded into memory. This is needed when
             continuing a model training.
 
-        load_with_mpi : bool
+        load_with_mpi : bool or None
             Can be used to actively enable/disable MPI during loading.
             Default is None, so that the MPI parameters set during
             training/saving of the model are not overwritten.
@@ -247,7 +258,7 @@ 
Source code for mala.network.runner
             MPI already has to be activated here, if it was not activated
             during training!
 
-        load_with_gpu : bool
+        load_with_gpu : bool or None
             Can be used to actively enable/disable GPU during loading.
             Default is None, so that the GPU parameters set during
             training/saving of the model are not overwritten.
@@ -256,6 +267,14 @@ 
Source code for mala.network.runner
             activated during training. Can also be used to activate a CPU
             based inference, by setting it to False.
 
+        load_with_ddp : bool or None
+            Can be used to actively disable DDP (pytorch distributed
+            data parallel used for parallel training) during loading.
+            Default is None, which for loading a Trainer object will not
+            interfere with DDP settings. For Predictor and Tester class,
+            this command will automatically disable DDP during loading,
+            as inference is using MPI rather than DDP for parallelization.
+
         Return
         ------
         loaded_params : mala.common.parameters.Parameters
@@ -298,7 +317,13 @@ 
Source code for mala.network.runner
                 path, run_name + ".params." + params_format
             )
 
-        loaded_params = Parameters.load_from_json(loaded_params)
+        # Neither Predictor nor Runner classes can work with DDP.
+        if cls is mala.Trainer:
+            loaded_params = Parameters.load_from_json(loaded_params)
+        else:
+            loaded_params = Parameters.load_from_json(
+                loaded_params, force_no_ddp=True
+            )
 
         # MPI has to be specified upon loading, in contrast to GPU.
         if load_with_mpi is not None:
@@ -497,26 +522,29 @@ 
Source code for mala.network.runner
         """
         Prepare the Runner to run the Network.
 
-        This includes e.g. horovod setup.
+        This includes e.g. ddp setup.
         """
-        # See if we want to use horovod.
-        if self.parameters_full.use_horovod:
+        # See if we want to use ddp.
+        if self.parameters_full.use_ddp:
             if self.parameters_full.use_gpu:
                 # We cannot use "printout" here because this is supposed
                 # to happen on every rank.
+                size = dist.get_world_size()
+                rank = dist.get_rank()
+                local_rank = int(os.environ.get("LOCAL_RANK"))
                 if self.parameters_full.verbosity >= 2:
                     print(
                         "size=",
-                        hvd.size(),
+                        size,
                         "global_rank=",
-                        hvd.rank(),
+                        rank,
                         "local_rank=",
-                        hvd.local_rank(),
+                        local_rank,
                         "device=",
-                        torch.cuda.get_device_name(hvd.local_rank()),
+                        torch.cuda.get_device_name(local_rank),
                     )
                 # pin GPU to local rank
-                torch.cuda.set_device(hvd.local_rank())

+                torch.cuda.set_device(local_rank)

 

 
            

diff --git a/_modules/mala/network/trainer.html b/_modules/mala/network/trainer.html
index e9b942158..0542b02bc 100644
--- a/_modules/mala/network/trainer.html
+++ b/_modules/mala/network/trainer.html
@@ -81,18 +81,16 @@ 
Source code for mala.network.trainer
 from datetime import datetime
 from packaging import version
 
-try:
-    import horovod.torch as hvd
-except ModuleNotFoundError:
-    # Warning is thrown by Parameters class
-    pass
 import numpy as np
 import torch
+import torch.distributed as dist
+from torch.nn.parallel import DistributedDataParallel as DDP
 from torch import optim
 from torch.utils.data import DataLoader
 from torch.utils.tensorboard import SummaryWriter
 
 from mala.common.parameters import printout
+from mala.common.parallelizer import get_local_rank
 from mala.datahandling.fast_tensor_dataset import FastTensorDataset
 from mala.network.runner import Runner
 from mala.datahandling.lazy_load_dataset_single import LazyLoadDatasetSingle
@@ -122,6 +120,16 @@ 
Source code for mala.network.trainer
     def __init__(self, params, network, data, optimizer_dict=None):
         # copy the parameters into the class.
         super(Trainer, self).__init__(params, network, data)
+
+        if self.parameters_full.use_ddp:
+            printout("DDP activated, wrapping model in DDP.", min_verbosity=1)
+            # JOSHR: using streams here to maintain compatibility with
+            # graph capture
+            s = torch.cuda.Stream()
+            with torch.cuda.stream(s):
+                self.network = DDP(self.network)
+            torch.cuda.current_stream().wait_stream(s)
+
         self.final_test_loss = float("inf")
         self.initial_test_loss = float("inf")
         self.final_validation_loss = float("inf")
@@ -135,7 +143,7 @@ 
Source code for mala.network.trainer
         self.validation_data_loaders = []
         self.test_data_loaders = []
 
-        # Samplers for the horovod case.
+        # Samplers for the ddp case.
         self.train_sampler = None
         self.test_sampler = None
         self.validation_sampler = None
@@ -274,6 +282,9 @@ 
Source code for mala.network.trainer
             params_format=params_format,
             load_runner=load_runner,
             prepare_data=prepare_data,
+            load_with_gpu=None,
+            load_with_mpi=None,
+            load_with_ddp=None,
         )

 
     @classmethod
@@ -303,7 +314,11 @@ 
Source code for mala.network.trainer
             The trainer that was loaded from the file.
         """
         # First, load the checkpoint.
-        checkpoint = torch.load(file)
+        if params.use_ddp:
+            map_location = {"cuda:%d" % 0: "cuda:%d" % get_local_rank()}
+            checkpoint = torch.load(file, map_location=map_location)
+        else:
+            checkpoint = torch.load(file)
 
         # Now, create the Trainer class with it.
         loaded_trainer = Trainer(
@@ -332,11 +347,17 @@ 
Source code for mala.network.trainer
             )
 
         # Collect and average all the losses from all the devices
-        if self.parameters_full.use_horovod:
-            vloss = self.__average_validation(vloss, "average_loss")
+        if self.parameters_full.use_ddp:
+            vloss = self.__average_validation(
+                vloss, "average_loss", self.parameters._configuration["device"]
+            )
             self.initial_validation_loss = vloss
-            if self.data.test_data_set is not None:
-                tloss = self.__average_validation(tloss, "average_loss")
+            if self.data.test_data_sets:
+                tloss = self.__average_validation(
+                    tloss,
+                    "average_loss",
+                    self.parameters._configuration["device"],
+                )
                 self.initial_test_loss = tloss
 
         printout(
@@ -377,7 +398,7 @@ 
Source code for mala.network.trainer
             )
 
             # train sampler
-            if self.parameters_full.use_horovod:
+            if self.train_sampler:
                 self.train_sampler.set_epoch(epoch)
 
             # shuffle dataset if necessary
@@ -482,8 +503,12 @@ 
Source code for mala.network.trainer
                 self.parameters.during_training_metric,
             )
 
-            if self.parameters_full.use_horovod:
-                vloss = self.__average_validation(vloss, "average_loss")
+            if self.parameters_full.use_ddp:
+                vloss = self.__average_validation(
+                    vloss,
+                    "average_loss",
+                    self.parameters._configuration["device"],
+                )
             if self.parameters_full.verbosity > 1:
                 printout(
                     "Epoch {0}: validation data loss: {1}, "
@@ -602,8 +627,12 @@ 
Source code for mala.network.trainer
                 "validation",
                 self.parameters.after_before_training_metric,
             )
-            if self.parameters_full.use_horovod:
-                vloss = self.__average_validation(vloss, "average_loss")
+            if self.parameters_full.use_ddp:
+                vloss = self.__average_validation(
+                    vloss,
+                    "average_loss",
+                    self.parameters._configuration["device"],
+                )
 
         # Calculate final loss.
         self.final_validation_loss = vloss
@@ -616,8 +645,12 @@ 
Source code for mala.network.trainer
                 "test",
                 self.parameters.after_before_training_metric,
             )
-            if self.parameters_full.use_horovod:
-                tloss = self.__average_validation(tloss, "average_loss")
+            if self.parameters_full.use_ddp:
+                tloss = self.__average_validation(
+                    tloss,
+                    "average_loss",
+                    self.parameters._configuration["device"],
+                )
             printout("Final test data loss: ", tloss, min_verbosity=0)
         self.final_test_loss = tloss
 
@@ -642,16 +675,16 @@ 
Source code for mala.network.trainer
         if optimizer_dict is not None:
             self.last_epoch = optimizer_dict["epoch"] + 1
 
-        # Scale the learning rate according to horovod.
-        if self.parameters_full.use_horovod:
-            if hvd.size() > 1 and self.last_epoch == 0:
+        # Scale the learning rate according to ddp.
+        if self.parameters_full.use_ddp:
+            if dist.get_world_size() > 1 and self.last_epoch == 0:
                 printout(
                     "Rescaling learning rate because multiple workers are"
                     " used for training.",
                     min_verbosity=1,
                 )
                 self.parameters.learning_rate = (
-                    self.parameters.learning_rate * hvd.size()
+                    self.parameters.learning_rate * dist.get_world_size()
                 )
 
         # Choose an optimizer to use.
@@ -690,16 +723,10 @@ 
Source code for mala.network.trainer
             self.patience_counter = optimizer_dict["early_stopping_counter"]
             self.last_loss = optimizer_dict["early_stopping_last_loss"]
 
-        if self.parameters_full.use_horovod:
+        if self.parameters_full.use_ddp:
             # scaling the batch size for multiGPU per node
             # self.batch_size= self.batch_size*hvd.local_size()
 
-            compression = (
-                hvd.Compression.fp16
-                if self.parameters_full.running.use_compression
-                else hvd.Compression.none
-            )
-
             # If lazy loading is used we do not shuffle the data points on
             # their own, but rather shuffle them
             # by shuffling the files themselves and then reading file by file
@@ -712,17 +739,16 @@ 
Source code for mala.network.trainer
             self.train_sampler = (
                 torch.utils.data.distributed.DistributedSampler(
                     self.data.training_data_sets[0],
-                    num_replicas=hvd.size(),
-                    rank=hvd.rank(),
+                    num_replicas=dist.get_world_size(),
+                    rank=dist.get_rank(),
                     shuffle=do_shuffle,
                 )
             )
-
             self.validation_sampler = (
                 torch.utils.data.distributed.DistributedSampler(
                     self.data.validation_data_sets[0],
-                    num_replicas=hvd.size(),
-                    rank=hvd.rank(),
+                    num_replicas=dist.get_world_size(),
+                    rank=dist.get_rank(),
                     shuffle=False,
                 )
             )
@@ -731,25 +757,12 @@ 
Source code for mala.network.trainer
                 self.test_sampler = (
                     torch.utils.data.distributed.DistributedSampler(
                         self.data.test_data_sets[0],
-                        num_replicas=hvd.size(),
-                        rank=hvd.rank(),
+                        num_replicas=dist.get_world_size(),
+                        rank=dist.get_rank(),
                         shuffle=False,
                     )
                 )
 
-            # broadcaste parameters and optimizer state from root device to
-            # other devices
-            hvd.broadcast_parameters(self.network.state_dict(), root_rank=0)
-            hvd.broadcast_optimizer_state(self.optimizer, root_rank=0)
-
-            # Wraps the opimizer for multiGPU operation
-            self.optimizer = hvd.DistributedOptimizer(
-                self.optimizer,
-                named_parameters=self.network.named_parameters(),
-                compression=compression,
-                op=hvd.Average,
-            )
-
         # Instantiate the learning rate scheduler, if necessary.
         if self.parameters.learning_rate_scheduler == "ReduceLROnPlateau":
             self.scheduler = optim.lr_scheduler.ReduceLROnPlateau(
@@ -776,7 +789,7 @@ 
Source code for mala.network.trainer
         do_shuffle = self.parameters.use_shuffling_for_samplers
         if (
             self.data.parameters.use_lazy_loading
-            or self.parameters_full.use_horovod
+            or self.parameters_full.use_ddp
         ):
             do_shuffle = False
 
@@ -872,9 +885,15 @@ 
Source code for mala.network.trainer
                             enabled=self.parameters.use_mixed_precision
                         ):
                             prediction = network(input_data)
-                            loss = network.calculate_loss(
-                                prediction, target_data
-                            )
+                            if self.parameters_full.use_ddp:
+                                # JOSHR: We have to use "module" here to access custom method of DDP wrapped model
+                                loss = network.module.calculate_loss(
+                                    prediction, target_data
+                                )
+                            else:
+                                loss = network.calculate_loss(
+                                    prediction, target_data
+                                )
 
                         if self.gradscaler:
                             self.gradscaler.scale(loss).backward()
@@ -890,7 +909,7 @@ 
Source code for mala.network.trainer
 
                 # Capture graph
                 self.train_graph = torch.cuda.CUDAGraph()
-                self.network.zero_grad(set_to_none=True)
+                network.zero_grad(set_to_none=True)
                 with torch.cuda.graph(self.train_graph):
                     with torch.cuda.amp.autocast(
                         enabled=self.parameters.use_mixed_precision
@@ -899,9 +918,14 @@ 
Source code for mala.network.trainer
                             self.static_input_data
                         )
 
-                        self.static_loss = network.calculate_loss(
-                            self.static_prediction, self.static_target_data
-                        )
+                        if self.parameters_full.use_ddp:
+                            self.static_loss = network.module.calculate_loss(
+                                self.static_prediction, self.static_target_data
+                            )
+                        else:
+                            self.static_loss = network.calculate_loss(
+                                self.static_prediction, self.static_target_data
+                            )
 
                     if self.gradscaler:
                         self.gradscaler.scale(self.static_loss).backward()
@@ -927,7 +951,12 @@ 
Source code for mala.network.trainer
                     torch.cuda.nvtx.range_pop()
 
                     torch.cuda.nvtx.range_push("loss")
-                    loss = network.calculate_loss(prediction, target_data)
+                    if self.parameters_full.use_ddp:
+                        loss = network.module.calculate_loss(
+                            prediction, target_data
+                        )
+                    else:
+                        loss = network.calculate_loss(prediction, target_data)
                     # loss
                     torch.cuda.nvtx.range_pop()
 
@@ -950,7 +979,10 @@ 
Source code for mala.network.trainer
                 return loss
         else:
             prediction = network(input_data)
-            loss = network.calculate_loss(prediction, target_data)
+            if self.parameters_full.use_ddp:
+                loss = network.module.calculate_loss(prediction, target_data)
+            else:
+                loss = network.calculate_loss(prediction, target_data)
             loss.backward()
             self.optimizer.step()
             self.optimizer.zero_grad()
@@ -1026,9 +1058,14 @@ 
Source code for mala.network.trainer
                                             enabled=self.parameters.use_mixed_precision
                                         ):
                                             prediction = network(x)
-                                            loss = network.calculate_loss(
-                                                prediction, y
-                                            )
+                                            if self.parameters_full.use_ddp:
+                                                loss = network.module.calculate_loss(
+                                                    prediction, y
+                                                )
+                                            else:
+                                                loss = network.calculate_loss(
+                                                    prediction, y
+                                                )
                                 torch.cuda.current_stream(
                                     self.parameters._configuration["device"]
                                 ).wait_stream(s)
@@ -1052,10 +1089,16 @@ 
Source code for mala.network.trainer
                                                 self.static_input_validation
                                             )
                                         )
-                                        self.static_loss_validation = network.calculate_loss(
-                                            self.static_prediction_validation,
-                                            self.static_target_validation,
-                                        )
+                                        if self.parameters_full.use_ddp:
+                                            self.static_loss_validation = network.module.calculate_loss(
+                                                self.static_prediction_validation,
+                                                self.static_target_validation,
+                                            )
+                                        else:
+                                            self.static_loss_validation = network.calculate_loss(
+                                                self.static_prediction_validation,
+                                                self.static_target_validation,
+                                            )
 
                             if self.validation_graph:
                                 self.static_input_validation.copy_(x)
@@ -1069,9 +1112,14 @@ 
Source code for mala.network.trainer
                                     enabled=self.parameters.use_mixed_precision
                                 ):
                                     prediction = network(x)
-                                    loss = network.calculate_loss(
-                                        prediction, y
-                                    )
+                                    if self.parameters_full.use_ddp:
+                                        loss = network.module.calculate_loss(
+                                            prediction, y
+                                        )
+                                    else:
+                                        loss = network.calculate_loss(
+                                            prediction, y
+                                        )
                                     validation_loss_sum += loss
                             if (
                                 batchid != 0
@@ -1103,9 +1151,16 @@ 
Source code for mala.network.trainer
                             x = x.to(self.parameters._configuration["device"])
                             y = y.to(self.parameters._configuration["device"])
                             prediction = network(x)
-                            validation_loss_sum += network.calculate_loss(
-                                prediction, y
-                            ).item()
+                            if self.parameters_full.use_ddp:
+                                validation_loss_sum += (
+                                    network.module.calculate_loss(
+                                        prediction, y
+                                    ).item()
+                                )
+                            else:
+                                validation_loss_sum += network.calculate_loss(
+                                    prediction, y
+                                ).item()
                             batchid += 1
 
             validation_loss = validation_loss_sum.item() / batchid
@@ -1265,8 +1320,8 @@ 
Source code for mala.network.trainer
 
         # Next, we save all the other objects.
 
-        if self.parameters_full.use_horovod:
-            if hvd.rank() != 0:
+        if self.parameters_full.use_ddp:
+            if dist.get_rank() != 0:
                 return
         if self.scheduler is None:
             save_dict = {
@@ -1290,10 +1345,11 @@ 
Source code for mala.network.trainer
         self.save_run(self.parameters.checkpoint_name, save_runner=True)
 
     @staticmethod
-    def __average_validation(val, name):
+    def __average_validation(val, name, device="cpu"):
         """Average validation over multiple parallel processes."""
-        tensor = torch.tensor(val)
-        avg_loss = hvd.allreduce(tensor, name=name, op=hvd.Average)
+        tensor = torch.tensor(val, device=device)
+        dist.all_reduce(tensor)
+        avg_loss = tensor / dist.get_world_size()
         return avg_loss.item()

 

 
diff --git a/_sources/advanced_usage/trainingmodel.rst.txt b/_sources/advanced_usage/trainingmodel.rst.txt
index ddb429368..4413ab078 100644
--- a/_sources/advanced_usage/trainingmodel.rst.txt
+++ b/_sources/advanced_usage/trainingmodel.rst.txt
@@ -220,3 +220,68 @@ via
 
 The full path for ``path_to_visualization`` can be accessed via
 ``trainer.full_visualization_path``.
+
+
+Training in parallel
+********************
+
+If large models or large data sets are employed, training may be slow even
+if a GPU is used. In this case, multiple GPUs can be employed with MALA
+using the ``DistributedDataParallel`` (DDP) formalism of the ``torch`` library.
+To use DDP, make sure you have `NCCL `_
+installed on your system.
+
+To activate and use DDP in MALA, almost no modification of your training script
+is necessary. Simply activate DDP in your ``Parameters`` object. Make sure to
+also enable GPU, since parallel training is currently only supported on GPUs.
+
+      .. code-block:: python
+
+            parameters = mala.Parameters()
+            parameters.use_gpu = True
+            parameters.use_ddp = True
+
+MALA is now set up for parallel training. DDP works across multiple compute
+nodes on HPC infrastructure as well as on a single machine hosting multiple
+GPUs. While essentially no modification of the python script is necessary, some
+modifications for calling the python script may be necessary, to ensure
+that DDP has all the information it needs for inter/intra-node communication.
+This setup *may* differ across machines/clusters. During testing, the
+following setup was confirmed to work on an HPC cluster using the
+``slurm`` scheduler.
+
+    .. code-block:: bash
+
+        #SBATCH --nodes=NUMBER_OF_NODES
+        #SBATCH --ntasks-per-node=NUMBER_OF_TASKS_PER_NODE
+        #SBATCH --gres=gpu:NUMBER_OF_TASKS_PER_NODE
+        # Add more arguments as needed
+        ...
+
+        # Load more modules as needed
+        ...
+
+        # This port can be arbitrarily chosen.
+        # Given here is the torchrun default
+        export MASTER_PORT=29500
+
+        # Find out the host node.
+        echo "NODELIST="${SLURM_NODELIST}
+        master_addr=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1)
+        export MASTER_ADDR=$master_addr
+        echo "MASTER_ADDR="$MASTER_ADDR
+
+        # Run using srun.
+        srun -u bash -c '
+        # Export additional per process variables
+        export RANK=$SLURM_PROCID
+        export LOCAL_RANK=$SLURM_LOCALID
+        export WORLD_SIZE=$SLURM_NTASKS
+
+        python3 -u  training.py
+        '
+
+An overview of environment variables to be set can be found `in the official documentation `_.
+A general tutorial on DDP itself can be found `here `_.
+
+
diff --git a/advanced_usage/trainingmodel.html b/advanced_usage/trainingmodel.html
index c9496550d..42d3ddf23 100644
--- a/advanced_usage/trainingmodel.html
+++ b/advanced_usage/trainingmodel.html
@@ -52,6 +52,7 @@
 
  • Checkpointing a training run
    • 
 
  • Using lazy loading
    • 
 
  • Using tensorboard
    • 
+
  • Training in parallel
    • 
 
 
 
  • Storing data with OpenPMD
    • 
@@ -297,6 +298,66 @@ 
    Using tensorboardpath_to_visualization can be accessed via
 trainer.full_visualization_path.
    
 
    
+
    
+
    Training in parallel
    
+
    If large models or large data sets are employed, training may be slow even
+if a GPU is used. In this case, multiple GPUs can be employed with MALA
+using the DistributedDataParallel (DDP) formalism of the torch library.
+To use DDP, make sure you have NCCL
+installed on your system.
    
+
    To activate and use DDP in MALA, almost no modification of your training script
+is necessary. Simply activate DDP in your Parameters object. Make sure to
+also enable GPU, since parallel training is currently only supported on GPUs.
    
+
    
+
    parameters = mala.Parameters()
+parameters.use_gpu = True
+parameters.use_ddp = True
+
    
+
    
+
    
+
    MALA is now set up for parallel training. DDP works across multiple compute
+nodes on HPC infrastructure as well as on a single machine hosting multiple
+GPUs. While essentially no modification of the python script is necessary, some
+modifications for calling the python script may be necessary, to ensure
+that DDP has all the information it needs for inter/intra-node communication.
+This setup may differ across machines/clusters. During testing, the
+following setup was confirmed to work on an HPC cluster using the
+slurm scheduler.
    
+
    
+
    #SBATCH --nodes=NUMBER_OF_NODES
+#SBATCH --ntasks-per-node=NUMBER_OF_TASKS_PER_NODE
+#SBATCH --gres=gpu:NUMBER_OF_TASKS_PER_NODE
+# Add more arguments as needed
+...
+
+# Load more modules as needed
+...
+
+# This port can be arbitrarily chosen.
+# Given here is the torchrun default
+export MASTER_PORT=29500
+
+# Find out the host node.
+echo "NODELIST="${SLURM_NODELIST}
+master_addr=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1)
+export MASTER_ADDR=$master_addr
+echo "MASTER_ADDR="$MASTER_ADDR
+
+# Run using srun.
+srun -u bash -c '
+# Export additional per process variables
+export RANK=$SLURM_PROCID
+export LOCAL_RANK=$SLURM_LOCALID
+export WORLD_SIZE=$SLURM_NTASKS
+
+python3 -u  training.py
+'
+
    
+
    
+
    
+
    An overview of environment variables to be set can be found in the official documentation.
+A general tutorial on DDP itself can be found here.
    
+
    
 
    
 
 
diff --git a/api/mala.common.parallelizer.html b/api/mala.common.parallelizer.html
index c514c134a..3337f8b5c 100644
--- a/api/mala.common.parallelizer.html
+++ b/api/mala.common.parallelizer.html
@@ -231,14 +231,14 @@
 
 
 
    
-
    
-set_horovod_status(new_value)[source]
    
-
    Set the horovod status.
    
-
    By setting the horovod status via this function it can be ensured that
+
    
+set_ddp_status(new_value)[source]
    
+
    Set the ddp status.
    
+
    By setting the ddp status via this function it can be ensured that
 printing works in parallel. The Parameters class does that for the user.
    
 
    
 
    Parameters
    
-
    new_value (bool) – Value the horovod status has.
    
+
    new_value (bool) – Value the ddp status has.
    
 
    
 
    
 
    
@@ -261,11 +261,11 @@
 
    
 set_mpi_status(new_value)[source]
    
 
    Set the MPI status.
    
-
    By setting the horovod status via this function it can be ensured that
+
    By setting the MPI status via this function it can be ensured that
 printing works in parallel. The Parameters class does that for the user.
    
 
    
 
    Parameters
    
-
    new_value (bool) – Value the horovod status has.
    
+
    new_value (bool) – Value the MPI status has.
    
 
    
 
    
 
    
diff --git a/api/mala.common.parameters.html b/api/mala.common.parameters.html
index fb05f2aa0..ae7eb5f13 100644
--- a/api/mala.common.parameters.html
+++ b/api/mala.common.parameters.html
@@ -209,7 +209,7 @@
 
 
    
 
    
-classmethod load_from_file(file, save_format='json', no_snapshots=False)[source]
    
+classmethod load_from_file(file, save_format='json', no_snapshots=False, force_no_ddp=False)[source]
 
    Load a Parameters object from a file.
    
 
    
 
    Parameters
    
@@ -232,7 +232,7 @@
 
 
    
 
    
-classmethod load_from_json(file, no_snapshots=False)[source]
    
+classmethod load_from_json(file, no_snapshots=False, force_no_ddp=False)[source]
 
    Load a Parameters object from a json file.
    
 
    
 
    Parameters
    
@@ -364,15 +364,15 @@
 
    
 
 
    
-
    
-property use_gpu
    
-
    Control whether or not a GPU is used (provided there is one).
    
+
    
+property use_ddp
    
+
    Control whether or not dd is used for parallel training.
    
 
    
 
 
    
-
    
-property use_horovod
    
-
    Control whether or not horovod is used for parallel training.
    
+
    
+property use_gpu
    
+
    Control whether or not a GPU is used (provided there is one).
    
 
    
 
 
    
@@ -384,7 +384,7 @@
 
    
 
    
 property use_mpi
    
-
    Control whether or not horovod is used for parallel training.
    
+
    Control whether or not MPI is used for paralle inference.
    
 
    
 
 
    
@@ -1261,18 +1261,6 @@
 
    
 
    
 
-
    
-
    
-use_compression
    
-
    If True and horovod is used, horovod compression will be used for
-allreduce communication. This can improve performance.
    
-
    
-
    Type
    
-
    bool
    
-
    
-
    
-
    
-
 
    
 
    
 num_workers
    
diff --git a/api/mala.datahandling.data_scaler.html b/api/mala.datahandling.data_scaler.html
index d7d76df71..09ef3554a 100644
--- a/api/mala.datahandling.data_scaler.html
+++ b/api/mala.datahandling.data_scaler.html
@@ -109,7 +109,7 @@
 
    DataScaler class for scaling DFT data.
    
 
    
 
    
-class DataScaler(typestring, use_horovod=False)[source]
    
+class DataScaler(typestring, use_ddp=False)[source]
 
    Bases: object
    
 
    Scales input and output data.
    
 
    Sort of emulates the functionality of the scikit-learn library, but by
@@ -130,7 +130,7 @@
 0…1)
    
 
 
    
-
  • use_horovod (bool) – If True, the DataScaler will use horovod to check that data is
+
  • use_ddp (bool) – If True, the DataScaler will use ddp to check that data is
 only saved on the root process in parallel execution.
    • 
 
 
    
diff --git a/api/mala.datahandling.lazy_load_dataset.html b/api/mala.datahandling.lazy_load_dataset.html
index c10123f39..efcd218b3 100644
--- a/api/mala.datahandling.lazy_load_dataset.html
+++ b/api/mala.datahandling.lazy_load_dataset.html
@@ -127,7 +127,7 @@
 
  • output_data_scaler (mala.datahandling.data_scaler.DataScaler) – Used to scale the output data.
    • 
 
  • descriptor_calculator (mala.descriptors.descriptor.Descriptor) – Used to do unit conversion on input data.
    • 
 
  • target_calculator (mala.targets.target.Target or derivative) – Used to do unit conversion on output data.
    • 
-
  • use_horovod (bool) – If true, it is assumed that horovod is used.
    • 
+
  • use_ddp (bool) – If true, it is assumed that ddp is used.
    • 
 
  • input_requires_grad (bool) – If True, then the gradient is stored for the inputs.
    • 
 
 
diff --git a/api/mala.datahandling.lazy_load_dataset_single.html b/api/mala.datahandling.lazy_load_dataset_single.html
index dd16dddb1..5594777f6 100644
--- a/api/mala.datahandling.lazy_load_dataset_single.html
+++ b/api/mala.datahandling.lazy_load_dataset_single.html
@@ -127,7 +127,7 @@
 
  • output_data_scaler (mala.datahandling.data_scaler.DataScaler) – Used to scale the output data.
    • 
 
  • descriptor_calculator (mala.descriptors.descriptor.Descriptor) – Used to do unit conversion on input data.
    • 
 
  • target_calculator (mala.targets.target.Target or derivative) – Used to do unit conversion on output data.
    • 
-
  • use_horovod (bool) – If true, it is assumed that horovod is used.
    • 
+
  • use_ddp (bool) – If true, it is assumed that ddp is used.
    • 
 
  • input_requires_grad (bool) – If True, then the gradient is stored for the inputs.
    • 
 
 
diff --git a/api/mala.network.runner.html b/api/mala.network.runner.html
index 99a0f7135..3925b45ef 100644
--- a/api/mala.network.runner.html
+++ b/api/mala.network.runner.html
@@ -132,7 +132,7 @@
 
    
 
    
 
    
-classmethod load_run(run_name, path='./', zip_run=True, params_format='json', load_runner=True, prepare_data=False, load_with_mpi=None, load_with_gpu=None)[source]
    
+classmethod load_run(run_name, path='./', zip_run=True, params_format='json', load_runner=True, prepare_data=False, load_with_mpi=None, load_with_gpu=None, load_with_ddp=None)[source]
 
    Load a run.
    
 
    
 
    Parameters
    
@@ -146,19 +146,25 @@
 
  • load_runner (bool) – If True, a Runner object will be created/loaded for further use.
    • 
 
  • prepare_data (bool) – If True, the data will be loaded into memory. This is needed when
 continuing a model training.
    • 
-
  • load_with_mpi (bool) – Can be used to actively enable/disable MPI during loading.
+
  • load_with_mpi (bool or None) – Can be used to actively enable/disable MPI during loading.
 Default is None, so that the MPI parameters set during
 training/saving of the model are not overwritten.
 If MPI is to be used in concert with GPU during training,
 MPI already has to be activated here, if it was not activated
 during training!
    • 
-
  • load_with_gpu (bool) – Can be used to actively enable/disable GPU during loading.
+
  • load_with_gpu (bool or None) – Can be used to actively enable/disable GPU during loading.
 Default is None, so that the GPU parameters set during
 training/saving of the model are not overwritten.
 If MPI is to be used in concert with GPU during training,
 it is advised that GPU usage is activated here, if it was not
 activated during training. Can also be used to activate a CPU
 based inference, by setting it to False.
    • 
+
  • load_with_ddp (bool or None) – Can be used to actively disable DDP (pytorch distributed
+data parallel used for parallel training) during loading.
+Default is None, which for loading a Trainer object will not
+interfere with DDP settings. For Predictor and Tester class,
+this command will automatically disable DDP during loading,
+as inference is using MPI rather than DDP for parallelization.
    • 
 
 
    
 
    Returns
    
diff --git a/genindex.html b/genindex.html
index d47e3e9ee..fd258fb43 100644
--- a/genindex.html
+++ b/genindex.html
@@ -1609,7 +1609,7 @@ 
    S
    
 
       
  • set_current_verbosity() (in module mala.common.parallelizer)
 
    • 
-      
  • set_horovod_status() (in module mala.common.parallelizer)
+      
  • set_ddp_status() (in module mala.common.parallelizer)
 
    • 
       
  • set_lammps_instance() (in module mala.common.parallelizer)
 
    • 
@@ -1769,7 +1769,7 @@ 
    U
    
         
  • (TrajectoryAnalyzer method)
 
    • 
       
-      
  • use_compression (ParametersRunning attribute)
+      
  • use_ddp (Parameters property)
 
    • 
       
  • use_fast_tensor_data_set (ParametersData attribute)
 
    • 
@@ -1779,8 +1779,6 @@ 
    U
    
 
   
   
      
-      
    • use_horovod (Parameters property)
-
      • 
       
    • use_lammps (Parameters property)
 
      • 
       
    • use_lazy_loading (ParametersData attribute)
diff --git a/objects.inv b/objects.inv
index de3ef5c884098c75d2820eaf9d31932c6fae24b5..79066ba44a5440322f7ea24434bf052018ca642c 100644
GIT binary patch
delta 6137
zcmV5VPa%CWH(~5Yf%AzB1x(UVSpRt9y!4sp*3--W&2zHJB79i-{KBJ%qk3%8D_tSb9w8=Do
z75bepEuEG&1!YESgsLpXm~`V2CMK1a4uF&O#wHzXF-VK($MvT_!nCLwGUX<;AoHI+
zGNs*<4qckliSc-|yEsn)D$;1k)HkhROe!yhD9TcV{ZZ0x@dOZ#Ff346M_fyxXT}VF
z{JcigTJ~ko%rZq)4Nnlq7jKlm!vgk3t@A#lhd=OzvkFyFK?HWlki=L4yhjlp%2RT}
zWImO~ZHex~_zfnf{n&~oKf*dHPZ3UYh%l_se&iVD6%A=>xFe~^=N^o>27j@x^csNz
zWLK1;=m@j&B_eZ&8k`{+9-9L5b@onVPp8*PP(r4$DV@(o
zFKMz*L!V0q(U3F;7$y9G$0
zmpM^6Qt5R55~1{*1K$}s98*-0BCeZU(skGKrUgRuk`fExl!5b(r1+)$D+fP+yccY5
z_ItF5XZd!RW=OnZ`-X^vfsx
zz~?%?3_Jz##oNqEL0UwZo;yIh^KvVb3~p(`rb6t2q-0;kI@HNALPWu-<#mCe#zzS7
z&S~(oE~Ox31s#zg7UstcM(`PbWR172kI(%Ej?*SAa1TY{Z*2L}?{PRyyTCnw6L})`
z|EZ*gT-z47+3lk)T3&V-tSZw2`*B
zRg{or5qZtyh!J0ENcxd1@k*K&Cs;!|*I?^%=Q{Pvmyuku8YFWaxE~XLnSR9Jx+7mj
zdS58c{p>`ENV}v5a%!)fWRlS?DDBWDa?;$RBOvps?pT~RE|RN=jz7MRpR_!r$D-4T
znjRlK`^{3n=(aSf^q@;MT)eckj2Oz7%G^^^4n0r(DG#T{
ztiU~FNr{+AP@Yco$SHjGnT?*#TUS42szA)lJHI)r5NwjNDlsfDov3-+-)af#
      >6
zP1#XFL~U^#NoS5+cf~CiLc3*)=f>YewBxB_r+K9>1m4ZC!)w*E+?z3Hv4{Ht%WY%qqp*#BzdsZ>R0ryb;w9kfANj>2^z5
zAbwbwn6}l`;Lx*s=Ju5A9^5-;bO+W{BBdW=70;xT@lE$aS~uPB+^5<)
zww-Ei!bcwa!#k^gNNLb{a0Y1F!4GBTyY`U`KQ=*TZJ2$sxb!)qF4j7(!~Ofa_fH>&
zie5EYn&Nsz-Ri|&
zIU%IhKzxCbNJ0u-*4PCUNhYlK`ChG+Snj_%31+Bsy9BE`%7qBl3HKSry^??-qDCJ5KIB}3Bo!w#eN*S@4_49$
znzzm^d{qrAP{ZA7x8~Pf3&hoIv`ye>N{Xo
z4$ND?*Fd`2A3qn49Bmcliuo$o#L?QHH5rzztPIG
zyhvn!CVj_%%a&x-P`Z&)gxXJ0O?by&D2or2HMKSq%b@P&V!bC}Pb}!JXIEF_BKZc^
zwvY{q){?&aOxmJ&Cvgl4cN*s-3He9@j0<*wb|v4Ssn9uwoPTu@J5C6lyB6@p)C6_R
zZaIB*%w9v>)a^n667CPOtC119Eh)lt(;9Vu7g5(}eH(RD4v$@0ESta}DK64*02%$>
zpPpO3kXe5cm6y;5Z(`Xoz{WG$w6tNAOl`8fp
z`c5vDk6oJ7ZA+UZXK7(e4#kqMxYtS)6O;!;bjkgtaA2gWb)^+GP>fFWQG!=j`w-oK
z5LV|w%ZOq4q5n)FNFN2yXMOQ=em&q&-WLCG%O3A~wrL@2$gEioM-YE&_rvI6sHL9G
zIq|EIYR^Bqr!+YX>7JFEza{->mU=gBy-+wR;ocL2zD4x1`qm)Hz8z2~o57gD9D0rJ
zZ(!Sx$x6#N@Yt%h5mo>}|vUdXtrFM-O%%Rt4*9NwBhZypeQrehzCHxMf
za&cGM5u+$f?mCUwQvZ|e!soy86pmkXZE6E6EKX%j9WNbYuemz|e1UX(cW9dVqBA)@
z?vBdv0J$}x@X6EQG&8VdWodm^IFN=va1CPIdH*S@r7ITHgnA}+(M3+pclZo{YUGe6
zPpQwj>Ka*@|8ueQg*O}PlL*xL88f5b#JgtP@s*T+lVn)gL%tGWYb+V0gGrn~ymUWT
z|9)PrrS|~A(UCwU+)&&S{qX7bj9>25LmI$x%o
zJ-+FPm90OKx`mn7%(2S{MjE((noGKMW2(mD<-F3iFF}kF&37uZq86x!+joz5%I{DV
z3>MIAPi}bS%zWuOq*L#fJ0c=EqURVQgq!5*l?h3!DWm(NHc_%#p~xCdZN=2u)r&Fb
zY4;UYYSjqU0M1&IR!~U3z2J`&VdS2H9Zj6MgUKn2g>tSyU!#yKX`I7<6H5%el%^^#
zqzyH{m2PwJ`S$Va{gYWU7%6V?zlnX&S2qh6zG+ZZ>gpDA?-jCF*F
znkontZF6&fYpNO@fjRQ}&TX4uIZG{Ro?j|q*s365Aa@DZJd+N7ODu*m?AFw6yiojqIRMB>zu8BZR@
zQLM5go4sAA>11M_Sx0GR?hfRwveXS=y;JpDtITLdEDaOC^&Vh&E^F%V$DoBerM5A`
zoe@(nyYZz=#R~o0lK*C6QyXC%#ZGyozE^h2Z)7vfGjE{Wrb`afaLU?N`x@+KL#!X}
zmCZ?&0)FPTzfyyL%!G8K?rapbV$Vlm$9JDZ;6ul}sMiYO^^6DhN?o8f#C-HID#(GT
zx&Viwd`vVbu^9#nXp^EbVldelGTI<&f8Rrxyf5n)P$!?Edcl2wYY2Ea@xPj^8zKMx
zu+j|<&k=@ONs6+JHeTkRS$zB
z+57f!(dCVQio^Ek)N%m-Z
zfmsEAYfV+oL{L}7Tm*I=6SMmU=vm@(@9uu?OB5}&5hs}))Ma&z*wS5<5prQ{_@g|*
zI!~hx-z(P{Gzg`jK%QyX`6liP#4pR~?-9LG81BII>uyZ{y%!VOt@O|?rPp>7kdvW^
zyb~9xIV5h5^cGbz>#H@LU@xfY{3OA5*nzVPhiHJd
zfbC(^+&wVA`NkKns}w7pn2dzfy44D)9F@!h>X1x7U0et54Oshm;Y!%Pc-?`Te1*6Y
znJz&vHC$dY-+;_+vDAGZwgI1eMOPdt-i+;~SoD{BZ2{d3LHp8|&&^^@X(LU{VG#0C#{y#L*K4fA&{QPYChUn#xD*aP@N
z!Mp1m`#Th!_b@$lYbUrzCLMuGU=t4=tC0;Ia;(EA+Lt#N{#g9zdL?X0J%BHDG47IY
zdjHir^zH^o*NSLym8Bs;sab3y0va2CmV3pI%;#<;pSW2R$P0d+z1xI>_pRlic*B>
z`Jr)x+=_2xBx{jut!^#g8cSOXYG++rz`1MR155{v+{%PDL9;cRwV2kn<|1OIHPMXWQod^bCYqS|+8ry9~c&^iDY`vMGnXPQvV3`|(MyM9{pdp^UNoWLYV-*?#
znj3~@fEMe*=77eAp)I7#M4C^3SIsfa)?|(FESF-9F^!E+V??7hU0XC$Yt|Uo*r2sQ
zw6$rCp{>nYW90Rgtucj(Eou%XExtK`v^1HGFuBKTKSSLLi`)p;$|$!))Gshv0%{ky
zjqq%Ya#KJ{yW9wNtnr%xZEbx8sMKZ_&3*o>Hu#0iQwO(b^vh^!7+ceS-vZeWs*QDM
z0c$nbS>n<==4oF?29I{c8ysYGM+E8BC>4mI`%KX8nOIdM3r)-_-~?jrlBgwz$>3rO
zd8r{gMMM&xLDK8gH5BL9oL7P6FlmAO9Y*2?aB*{-Bdu3yruNc}HGFh*0!bpi#Ej(Q
zgv*!Wtsr`bn!jcxgOo
zUxRHveOIE>8N12Z-d;{^*+_D%ix9S}>U8KBy2F&3&@^G<!l?ms_$`SAA7r{6+^
zlYb;-9NzpI_Mt37_)b2?AjLW4$s4MF#rYh04Hx5oR-Bvk`7tSSW{$
zXpS`~;tP#PS~PVRbXBv=$iHoa!Zv8cF+8oIgdd8k$|oijOD}`J0XL*qfb?5xHS$#c
zod^m+D1t^D34DfGS>c!gt+sNS{a0^z(JVZnHOl9t*$kp68%bgc_Z)2$>J;
zXB0n6V=^RZlGF-+edNC*2--Goy1Jw{y(qz^;_UhhIb=joHCcAU{5aBY?v&s|(FgJr
zei2V2P|=u~k`zg+CK~vqNdMP`ha|jJFcg5~nfgFY!rt%Gh@q8;8U)Vpmys9twy|@W
z8yV$8PR97>0W@Aed^9PG7{>I>2nl
zTNa=G>%e;ke9r4aFv8>v7Bf&x+wnjq6ldLv>^kO>i~`C|rE
z=o4YiFbSTpP#w!MNL~{)QxM2<99s^Vg`H^vi&8x#f1Uzfu84h8%Jf!+DGLf%IVc$1
zbu7Hiqzei#6ya#YuqC)dc}h;ye;}CzfaTKFMdFlyli)>G(jus*kFvh@H|rSi&P3zP
zGcSVK%c2)qy4$3?!fQk3f%rbSSgTW{enGyc>BCe+?8%r$NJ}Il#DIc(1+wDlea(cE
zU=?ExtJ08(ib@RhQH9LDZ7?k@E-az*044sVIh`yRgt*Khf)-d#fZpFgOwO`q-2sAF
z&ovW&i8Ic;Sl}JrGjGH?iNZN2!KRE69hoz@f>^{{;1_QflEJ-c4kNLDCY7v+EQa!B
zfk1t!y`H?4%q04Gq;I{!>~YeN3@n=be(kAKL?t7SGCZi
zD_W(}3AFc=YQZO$nuc;nV0;^-mT2(`$#Cv}O)zuK-YmuFTFJ0~4)izm=@4h`^$Uk#
z!Pr5}ETrrXFBA`f`jR#!&h$FBa1azM-!h<1-{9J;uzL)&7buy*%1+h7acH2vpu~`&
z^;I4Yf&%Te3#RbB)97#<8fZLD>nVn}DU9Z}fyuoE799OO2jR?%!0b8!8@@^9k6#6U
z29D@$2#2~b2oKD>gIlqURb%`rFms@-S9nQWA)Sju8TvH#`;UFkja{H-9HR=mT
zE<#m+GY%)iVOXGb^JqvQYw$QUSoUwIL?3!V47QG{MIp}9UZ6qJKVS>u6pt4Ec!=1W=5JYjkwQp|
z1pXLq6}6#aQJ?+|dNBbhNqmKWSzP8Y#3e)h4=&tp5W`};k=IA<1>T82ecVg=a+8!0
z-LOr>Zk(S(nGyY?dwWwS+vCWO#B&5BtK);RcsC-9E=0
z=vZ#K{9Y~q-=s(bCkuTg4`Ira`A->$v~fzv+N=UJT@ODW;VvR}k6wJ7<*z)&?mTj^NB8LyKdDqB`WD;4b991d4
z`P)o6=JXzfNk36tZ`v1NJQ<((F&f@uwA-Iu$Go%^E$@Q95f3*k*7BBUzkR8M9{0^8
zbBo)cQf@Tae7NEZAs*xwK~Tq+VMHD#c6a&v2a>9QOwRb>o#ATMQYOX=SZ{dz8#(^s
LHu(Po_BLuYsb

delta 6150
zcmV+h82RV!GW#-+Uko`lEoU`jW@Ip9I5n|sQ2~GAQr6{jnM4Q!+#vV(8OZYrMQK3@
ziWs^l$g9+4;z@r7YozUoxR|yd5@HVn;HB|kjB5nQUJ@OlzyRYqJvJCR15W@3o{-_O
zIs1Y}ah+DUWdv)1Q?fiI~lBN`*bNG>UH}(3%Nb
z395fI{^lhQIVc)3Y9a^|KebRm{8HB6{D2d+EUG*q21Rj7&rJ>B+oK+w63MnMlAheL+%rv))+
zlj;5{^gCf*IxTGq$_&>CRauHL>B=Ka%qlOP04M7WPCDRXkQUL8>ra1#X;C#~>P=`t
z=0AI6YP%;Lx-_Q~AfRqWds@gUM+>wxY?8u#U=8gwq@%3@fxBIfi*fLz)`yNGkHV2P3Y*U#u&=
zMxX%M6{RRT!mNCW$o!!OXGn&}roexEJ^nQk6PI-jGxk0rk%+QKaf8d#>9rD+kg04+
z=d{sFn(Wii=aNA*B+UVaNd&()X_g-Aw8>v9F;X*$aG8<6MGPYn6#H7|yc@0;u4MPE?LmI-S2nC_U%EcZLqf6jh{%>n4|U-Sxa_fe^i2kb9xdWoz8$6+60g|8A>w2j0J}9~ubkAHy!I0~-`Ydze)^^RW3aM+Uy%+s{prVg
zU8XwlxsERbPeFX~HnUQY77?cB576$s+{z?_TUxNG5PKjg*;la+b#jalQE+N`T_C9O
z5dyq(8vLwFDF|6XM`VbF`7wWk5qt(&<8AxnbH9n>v`>2bSmmLbL%Cx}#rt4EKVnl=Z62YqUwB*rJCQZ#2;r1&~(sN{2
z+L2ThC1hDdUh_C&#FrY9ek4o0lBUH8){xFM*t*=gPW|#_B$uoP$y|R2?#D!?A2GP@
z$XAix7mBk#J5eIiF6p71+AAlSWV8!PJG6aW;dYGc?jsB46gc%yq6obwNHy9kz#@
z{(uSHNr=;3a@FrW5u<-4LLjd)-%a2-MGYX6BY=HpaKJ=&z4m2`Kvlsap@Xa6rtkvO
z^96ex=AQafB~A@zfqTf35;60mJe}wfSNQBR8$F%3VP(oxftZ<+esfkK*d%3DVpw20
zDfG6N))LmqDe`=Jv!jBD+Wk0^&N#X5id!y(cFPvejlW56$5VgBPV;oRqLgmgwkM{S
zPmjxz>I38h$p`VIJu@@KHwQjEeoL#{x(3&;b&7S11DlxG9IKt5s}y$=%L(#*q_%7G
zMpQ#UhPE`PTRUZe_~B$?MpsvZL)Pw@+f%uFaPOSeJ@bdszGS_s4W*mkP52_Jdv4+^a!r9tPxd826uKa`p8+D9_{hz6M)`DS5SW7`rnK6GGO?lbX>N`5ZhQx|qC
zB|%sEiz(PfeK@5x!clu7a;fXtDKS(brU}w2fzRZ0XGMSI14R94idRirQ?!X9ZKq8r
zdevlUit811s~3CagpgVT@dZXA2`O}0V;4{)nXumHd$m?#x&P`Un4!+?60GVd7a~|Q
z9OxMSPUf5K6_s@MJO_{@2K|j|RuOK}Ze3GL$CrrF6E~!pmdi_mK2jj&`kvX@leyvw
zaZ|Nz#c6-e{^*$uRCYjQ$8d=0c2~dFV4yEs*oGsZs4d#1^Djg8N&<$68hP|vlyeP|
zRGbF&O`WGdSV<#j-a5DNRW+EmXGdu&?0Wf4bQYScoDNtGEr+=GwFhfevu#k
zfy^%HfOKuB?|@l3Fz*Cse^0fmWT`Og03kyWL?c6(~iRToDbj!{nT#^to9KVWAdaE~f
zio<`R*AVi?{YER#@*VQZ#4#w`X`GKFwSg5Dr?RF_o{q8C+?@fw
zK)Ss)W2PIjjYW7xmfzbn~n8J1nPX6nbB|JT{G_ZO3J@UGOX+&Ux~0a
zmJHItBu*e+x)ZE_Kd;u(dqBTr9~=o(!VSeO(GQ<)KitDI{V?Qvp9
zgem|msUtGT3GKBj6cUd}6R`x3+`(R`;e
zD{6syxPA9{r~D2@!C(Q+_T+|F+{~A*Lpt?txg#QyBYKV@Lbyq;UYU@znlietY7-@^
z6^g9U)K*NbUA-7{)OKHCrB;nl4dARbX$6JkM-2W*5k~GA*wMt9JD-1?vREkR3iLG!
zxst{?Jh8;kOKGa|LfTOCTj@3jpKl+(-anZ&g8`E*1zT`E(zEj16JiZflNl@THtIF1
zwvBO<`k7Lfz*t9!sHuWb(Ka{tx2CGm5tt*d?<`lbZPUNCjO&$PHDgV%&m|dGBS2kd
z_~bJ=c>QLqs(&CpLOFp8F(2yXzwLuuGIN;k8DlW<)XDyH=fX
zvfKBJJ3%IG+z)c;E=wJiNpC1I*;4S2%9w*_-n8r#aSQXx=DdY+U2EII$Q&#-F#1{M
z#}rDgxOZS)+u*mbZfyBl>fzw6Zibz#K_l#C|CrFIo8X8=10R3Ud8kd=Sp=I5@Cd_P
z(Al#^P9#npnepUd9K|Y2vf0~(nocI>nRS$A=I%h=Dofn});n;&waScU#L_Sw_($g$
zp39p0`!Q&tPN{8-aA(BSqi=jEQ?Wunx8%Q>*wjWCN3l~Lsqd9905Gx{=9xE8Zqp@)
zX*gwVt9=c2vmt-h5BJLEq)Gul^V(nEL1sd_QFk_qTCwM&u;aT=BJiPOUes#^@p{Gs
zd!;T=8)82C7!~9|R9%2WQ9dRbl-LY|1++=g7%`Y^3>j?@wZHEnOx~CE3#gONP`%(j
zz%>LsocLc&){T&V|MI7U^br)ti8@dpa?vGC5?Hu^{P=(P^vOX+DU8dUGCapwRo#TM
z3Q5}4&Ps$Frty%J)TeyXUv=sV*kK*DkTy#NcF1g>TkeK7;y%z@*;Be6`dbl~$&&Zr
zt)MOo`KkQ^olL2mbeTgye@Q(EpKvfj-y7<^2Q^2;F0{Z=4$wCbjI6)lzV$aX#_~u#
z*ri1GmYsj#%*(2W!IA8J`?%=xMnz(UPQ8O8*x&HBTry6nBCW;mn697SxneX~LK#b&
zYJrgM@?)@OGEX((5MxKFv1B_jb&7kj2N`!Ukt0|Wyf%#awo;tOcS6CB;4hxQH{~F<
zvv#h)Wz@whWWIE8iv=sAsbTn_OoG%|v;ZVeMu&e)EFjtNzAcT^9h|NXxQx0Egv?V1
zw^#=QINw>CQxR9o1gwRuuxLh|fpbp8f
ziP&M9wh}v3_H1Sd&jZUEIH?Zta=secm*Rs*_7RL4MwT?k6rW_iZ}BH}ybN!QYjVWi
z1r2{&?Hrw8-^3()G`+yAg0-e9XCkPpVlDzZkBQlR1N1EMxp#Lz_a%y!+K7|P4(hVH
zMr`S>$_TkIHvCbZV4bH?hwqi^3>t(|P$17V?0ge<1>%?G^!JF~UJQ3&`gJ#^|K5uU
z?N)kdm(pvy3CPJ%MBa&u)Ep8wM|xu`ne~6wnoh76)O3E5;5+jFeVVDqpb4@OB)c4l
ze$b~L5A49%g+nwzTfp|PY3?4F-+bc>*Hwy@PE1BZYTasuRE|n!0d+{GpDwNg_Xe!}
zyl^FKU%c)>O};{0iAMoGnQuU5w^-`F58Hsxy`n3Q6mQ1%QY`w*y*7aVKqr6a
zz;xu6rw7P2xZKY4nI
z*8s3cgdS-%M+@dOW#&e*9*Wm3?XD3f0|MF(DViR=CEW!WU+|L~@^(}!%iREtt`NG?
zlob}b8K${aZi8pgeVD<0hY`&*{()V=E$-l&L$Q_8VLz}HZnnj31s%1y?Qnndt!^u>
zy-{uii(q!5X+?*XQRMs8(7o1od6
z&00)rTXPXH)0%6U)?Q;0A9WU6rcML{ur=BYF^%muBRtpXGq&E$(9BjgZLrLZK_gTP
zd(aTi-Xt^vwy_Eg0nH6VGeCcfbzyTrW5duE(q$ser>o|eW^1xWc$Q1C#+b&&r!k_@
znyxLHsWoeiYi!V3Alllr#?aPgtugX?%hs5}#1=INlNR3`Kw6s2Mwr~=wV$DGg+*?J
zYh{#MBI*|yEdjL)+(vjdM!6}VrCn|WJJ$HkfVQ^20#s@2HDT2i3+pw1Bl5>@0EV9rLuWBZEgf;tdWmx+8-0YLp7Z(0wLo_e`uRl7%K_
z6>tKvc1hHd!(?!=g}l^|ogyNM&mie_>KcmkYtE~{a+tJ0{thE?1Gu<3&XLxuG*f%&
z#u`34I)Nk+Ut&h`al(J)OYv3_(HzCtEvn66Xa{RKB-((_w_6{zYtYtw(DJR+J+w+}
z+QMA4M*XDK9=tT3w6DQ7pS~;6>5SdvY;P~8wrnIh)
      0RdqUa4BcT$O=y}h@p6)y
zclV#4zI=H5=hJT?!pT39G7fKk4f{|QA$%tvW02w;^5hNGzv6#dBrTe{3%aUVX5``;H(g!Qn_iS)Q*n0vg&Z;>sG2Oh
zVSXIxH+M?#q38p73crY_5vXX)Oi7BQRTB;TQl$Uu!b1|?Di{ht@=Sf8CSmXQX~fV<
zL=6IG_{+!(d)wH#%#DolAtz(}^8lK;pJKir)1Pbr>-m3M2T4luR)}40F{17OI^Hfs
z`1GW5!4OgI4u@}emw4MIk0zS7`cZ=9+lv;Vei`2f(dcjMwJaoisS!DZ(!!_FC~LsO~$l%F4+Uk
zP!LQtNT+`o^H)3)|38k#?^1~P$c{P2ThRa
zCA|?bC&+||)ci4nD)fmkXP5*}Sg4L=86>ZXnkfimIgTxd%)-tzfkmkvl0Q!YFIU9A
zDP?-A!juICtQ-^!?m8CUX3_-(7>aPTVb~Jfp*(*jC+a_tOaj1i>FOeJ%1Q7dD`^qb
z(??lf`}Ao5EZuF=UE#GM^FVwbT&&e8QokVI)AV5~BKBlVBcvq~
z5n@2Wy#iVB^uA`oNwA8shE-|EL`5YA`lv!?-!_<*78jP#d4LlC(wt5f3_@Jy5J3wp
zCqRGiZy+XTS+ni{L9FMRiNqOaUM%nq@0mAZokZcBlVDTEh>pw|TtO^iF7S)D3(4T#
zG>4JcKa)yUL>5E&vOu7|)Lu{CN^++5DVV!Sa2{-IL`ngH!S&!;(3#uB!(mvUxg%Oj
zF}hAV?4JY8y{lU2(G{&y=>*z)O10pVOHF@6IV3Q?4N^ORW^a~abgg9A
zKL`4o`gDjh_xgpyuwd*UW)@O*hZl;6Kz&J@5@&jyTQ~>`mTwtQr*Cj=R@glT+6$D-
zU}dLj;W#uu?YhEV=zuqZ;*vBNw46z!`^=;V>-Fx_LAtkTrN58Z7%aRH6^PAcoyzu;8dq2`2gS
z3;F+G!LOVWMshtD^8dk-BQ!OR8n#E;=m%Fn8NZGs!EiywcE>?+-17x-2tpHn*|U@
zGE@-Ko~O{3K(X(rgc@y6hW&Fe-i(~ZkvA&CZt_C&P4l;`zDOaYMFM{ew~Bw-P_d{_{|3F7fRrS@!YnRx7~+zl{s$LsH;7>|-pK2t
z_5$z3pFZxTe7Q+Vh;G;>VmHpuq0ET>QNDyUh;Mk%pnvwzOsr~-%pc)&?^;5hN-{h-
zq=$Xs<#2<`n{JM*+Awjy-O+>$5N}5C-)TNYgWZ5s`ms*s3VPL3p3qq}?w!z`Y+fSb!9_LWU
zJ5UQE6GYZtW`w^(4cd1&!TMJN3f$!3Z;uaOetUep5C4;$N)E-TWZp&pSIaip1(CxC
z*t~1xMKXyjRgS6@-~4WErW|v655lCMsIE8d3!aQm{1^@IG1~3Vu47)>ik5dl--w4B
z7HfG+wBNo|LXZ1qlDWlgP$@T>Y(8A^g%A&Niy)}u%P=Aj6T7?o{R2r=KqhDW@Xl~G
YYbg`s1*|tb{*4@eaU1;q0Y~PRP}cFk{r~^~

diff --git a/searchindex.js b/searchindex.js
index 83b171891..e80348020 100644
--- a/searchindex.js
+++ b/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["CONTRIBUTE","advanced_usage","advanced_usage/descriptors","advanced_usage/hyperparameters","advanced_usage/openpmd","advanced_usage/predictions","advanced_usage/trainingmodel","api/mala","api/mala.common","api/mala.common.check_modules","api/mala.common.json_serializable","api/mala.common.parallelizer","api/mala.common.parameters","api/mala.common.physical_data","api/mala.datageneration","api/mala.datageneration.ofdft_initializer","api/mala.datageneration.trajectory_analyzer","api/mala.datahandling","api/mala.datahandling.data_converter","api/mala.datahandling.data_handler","api/mala.datahandling.data_handler_base","api/mala.datahandling.data_repo","api/mala.datahandling.data_scaler","api/mala.datahandling.data_shuffler","api/mala.datahandling.fast_tensor_dataset","api/mala.datahandling.lazy_load_dataset","api/mala.datahandling.lazy_load_dataset_single","api/mala.datahandling.multi_lazy_load_data_loader","api/mala.datahandling.snapshot","api/mala.descriptors","api/mala.descriptors.atomic_density","api/mala.descriptors.bispectrum","api/mala.descriptors.descriptor","api/mala.descriptors.lammps_utils","api/mala.descriptors.minterpy_descriptors","api/mala.interfaces","api/mala.interfaces.ase_calculator","api/mala.network","api/mala.network.acsd_analyzer","api/mala.network.hyper_opt","api/mala.network.hyper_opt_naswot","api/mala.network.hyper_opt_oat","api/mala.network.hyper_opt_optuna","api/mala.network.hyperparameter","api/mala.network.hyperparameter_acsd","api/mala.network.hyperparameter_naswot","api/mala.network.hyperparameter_oat","api/mala.network.hyperparameter_optuna","api/mala.network.multi_training_pruner","api/mala.network.naswot_pruner","api/mala.network.network","api/mala.network.objective_base","api/mala.network.objective_naswot","api/mala.network.predictor","api/mala.network.runner","api/mala.network.tester","api/mala.network.trainer","api/mala.targets","api/mala.targets.atomic_force","api/mala.targets.calculation_helpers","api/mala.targets.cube_parser","api/mala.targets.density","api/mala.targets.dos","api/mala.targets.ldos","api/mala.targets.target","api/mala.targets.xsf_parser","api/mala.version","api/modules","basic_usage","basic_usage/hyperparameters","basic_usage/more_data","basic_usage/predictions","basic_usage/trainingmodel","citing","index","install/installing_lammps","install/installing_mala","install/installing_qe","installation"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":5,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,"sphinx.ext.intersphinx":1,"sphinx.ext.viewcode":1,sphinx:56},filenames:["CONTRIBUTE.md","advanced_usage.rst","advanced_usage/descriptors.rst","advanced_usage/hyperparameters.rst","advanced_usage/openpmd.rst","advanced_usage/predictions.rst","advanced_usage/trainingmodel.rst","api/mala.rst","api/mala.common.rst","api/mala.common.check_modules.rst","api/mala.common.json_serializable.rst","api/mala.common.parallelizer.rst","api/mala.common.parameters.rst","api/mala.common.physical_data.rst","api/mala.datageneration.rst","api/mala.datageneration.ofdft_initializer.rst","api/mala.datageneration.trajectory_analyzer.rst","api/mala.datahandling.rst","api/mala.datahandling.data_converter.rst","api/mala.datahandling.data_handler.rst","api/mala.datahandling.data_handler_base.rst","api/mala.datahandling.data_repo.rst","api/mala.datahandling.data_scaler.rst","api/mala.datahandling.data_shuffler.rst","api/mala.datahandling.fast_tensor_dataset.rst","api/mala.datahandling.lazy_load_dataset.rst","api/mala.datahandling.lazy_load_dataset_single.rst","api/mala.datahandling.multi_lazy_load_data_loader.rst","api/mala.datahandling.snapshot.rst","api/mala.descriptors.rst","api/mala.descriptors.atomic_density.rst","api/mala.descriptors.bispectrum.rst","api/mala.descriptors.descriptor.rst","api/mala.descriptors.lammps_utils.rst","api/mala.descriptors.minterpy_descriptors.rst","api/mala.interfaces.rst","api/mala.interfaces.ase_calculator.rst","api/mala.network.rst","api/mala.network.acsd_analyzer.rst","api/mala.network.hyper_opt.rst","api/mala.network.hyper_opt_naswot.rst","api/mala.network.hyper_opt_oat.rst","api/mala.network.hyper_opt_optuna.rst","api/mala.network.hyperparameter.rst","api/mala.network.hyperparameter_acsd.rst","api/mala.network.hyperparameter_naswot.rst","api/mala.network.hyperparameter_oat.rst","api/mala.network.hyperparameter_optuna.rst","api/mala.network.multi_training_pruner.rst","api/mala.network.naswot_pruner.rst","api/mala.network.network.rst","api/mala.network.objective_base.rst","api/mala.network.objective_naswot.rst","api/mala.network.predictor.rst","api/mala.network.runner.rst","api/mala.network.tester.rst","api/mala.network.trainer.rst","api/mala.targets.rst","api/mala.targets.atomic_force.rst","api/mala.targets.calculation_helpers.rst","api/mala.targets.cube_parser.rst","api/mala.targets.density.rst","api/mala.targets.dos.rst","api/mala.targets.ldos.rst","api/mala.targets.target.rst","api/mala.targets.xsf_parser.rst","api/mala.version.rst","api/modules.rst","basic_usage.rst","basic_usage/hyperparameters.rst","basic_usage/more_data.rst","basic_usage/predictions.rst","basic_usage/trainingmodel.rst","citing.rst","index.md","install/installing_lammps.rst","install/installing_mala.rst","install/installing_qe.rst","installation.rst"],objects:{"":[[7,0,0,"-","mala"]],"mala.common":[[9,0,0,"-","check_modules"],[10,0,0,"-","json_serializable"],[11,0,0,"-","parallelizer"],[12,0,0,"-","parameters"],[13,0,0,"-","physical_data"]],"mala.common.check_modules":[[9,1,1,"","check_modules"]],"mala.common.json_serializable":[[10,2,1,"","JSONSerializable"]],"mala.common.json_serializable.JSONSerializable":[[10,3,1,"","from_json"],[10,3,1,"","to_json"]],"mala.common.parallelizer":[[11,1,1,"","barrier"],[11,1,1,"","finalize"],[11,1,1,"","get_comm"],[11,1,1,"","get_local_rank"],[11,1,1,"","get_rank"],[11,1,1,"","get_size"],[11,1,1,"","parallel_warn"],[11,1,1,"","printout"],[11,1,1,"","set_current_verbosity"],[11,1,1,"","set_horovod_status"],[11,1,1,"","set_lammps_instance"],[11,1,1,"","set_mpi_status"]],"mala.common.parameters":[[12,2,1,"","Parameters"],[12,2,1,"","ParametersBase"],[12,2,1,"","ParametersData"],[12,2,1,"","ParametersDataGeneration"],[12,2,1,"","ParametersDescriptors"],[12,2,1,"","ParametersHyperparameterOptimization"],[12,2,1,"","ParametersNetwork"],[12,2,1,"","ParametersRunning"],[12,2,1,"","ParametersTargets"]],"mala.common.parameters.Parameters":[[12,4,1,"","comment"],[12,4,1,"","data"],[12,4,1,"","debug"],[12,4,1,"","descriptors"],[12,5,1,"","device"],[12,4,1,"","hyperparameters"],[12,3,1,"","load_from_file"],[12,3,1,"","load_from_json"],[12,3,1,"","load_from_pickle"],[12,4,1,"","manual_seed"],[12,4,1,"","network"],[12,5,1,"","openpmd_configuration"],[12,5,1,"","openpmd_granularity"],[12,3,1,"","optuna_singlenode_setup"],[12,4,1,"","running"],[12,3,1,"","save"],[12,3,1,"","save_as_json"],[12,3,1,"","save_as_pickle"],[12,3,1,"","show"],[12,4,1,"","targets"],[12,5,1,"","use_gpu"],[12,5,1,"","use_horovod"],[12,5,1,"","use_lammps"],[12,5,1,"","use_mpi"],[12,5,1,"","verbosity"]],"mala.common.parameters.ParametersBase":[[12,3,1,"","from_json"],[12,3,1,"","show"],[12,3,1,"","to_json"]],"mala.common.parameters.ParametersData":[[12,4,1,"","data_splitting_type"],[12,4,1,"","descriptors_contain_xyz"],[12,4,1,"","input_rescaling_type"],[12,4,1,"","output_rescaling_type"],[12,4,1,"","shuffling_seed"],[12,4,1,"","snapshot_directories_list"],[12,4,1,"","use_fast_tensor_data_set"],[12,4,1,"","use_lazy_loading"],[12,4,1,"","use_lazy_loading_prefetch"]],"mala.common.parameters.ParametersDataGeneration":[[12,4,1,"","local_psp_name"],[12,4,1,"","local_psp_path"],[12,4,1,"","ofdft_friction"],[12,4,1,"","ofdft_kedf"],[12,4,1,"","ofdft_number_of_timesteps"],[12,4,1,"","ofdft_temperature"],[12,4,1,"","ofdft_timestep"],[12,4,1,"","trajectory_analysis_below_average_counter"],[12,4,1,"","trajectory_analysis_correlation_metric_cutoff"],[12,4,1,"","trajectory_analysis_denoising_width"],[12,4,1,"","trajectory_analysis_estimated_equilibrium"],[12,4,1,"","trajectory_analysis_temperature_tolerance_percent"]],"mala.common.parameters.ParametersDescriptors":[[12,4,1,"","atomic_density_sigma"],[12,5,1,"","bispectrum_cutoff"],[12,5,1,"","bispectrum_switchflag"],[12,4,1,"","bispectrum_twojmax"],[12,4,1,"","descriptor_type"],[12,4,1,"","descriptors_contain_xyz"],[12,4,1,"","lammps_compute_file"],[12,5,1,"","use_y_splitting"],[12,5,1,"","use_z_splitting"]],"mala.common.parameters.ParametersHyperparameterOptimization":[[12,4,1,"","direction"],[12,4,1,"","hlist"],[12,4,1,"","n_trials"],[12,5,1,"","number_training_per_trial"],[12,5,1,"","rdb_storage_heartbeat"],[12,3,1,"","show"],[12,5,1,"","trial_ensemble_evaluation"]],"mala.common.parameters.ParametersNetwork":[[12,4,1,"","nn_type"]],"mala.common.parameters.ParametersRunning":[[12,5,1,"","after_before_training_metric"],[12,4,1,"","checkpoint_name"],[12,4,1,"","checkpoints_each_epoch"],[12,5,1,"","during_training_metric"],[12,4,1,"","early_stopping_epochs"],[12,4,1,"","early_stopping_threshold"],[12,4,1,"","inference_data_grid"],[12,4,1,"","learning_rate"],[12,4,1,"","learning_rate_decay"],[12,4,1,"","learning_rate_patience"],[12,4,1,"","learning_rate_scheduler"],[12,4,1,"","max_number_epochs"],[12,4,1,"","mini_batch_size"],[12,4,1,"","num_workers"],[12,4,1,"","profiler_range"],[12,4,1,"","training_report_frequency"],[12,4,1,"","trainingtype"],[12,4,1,"","use_compression"],[12,5,1,"","use_graphs"],[12,4,1,"","use_mixed_precision"],[12,4,1,"","use_shuffling_for_samplers"],[12,4,1,"","visualisation"],[12,4,1,"","visualisation_dir"],[12,4,1,"","visualisation_dir_append_date"],[12,4,1,"","weight_decay"]],"mala.common.parameters.ParametersTargets":[[12,4,1,"","ldos_gridoffset_ev"],[12,4,1,"","ldos_gridsize"],[12,4,1,"","ldos_gridspacing_ev"],[12,4,1,"","pseudopotential_path"],[12,4,1,"","rdf_parameters"],[12,5,1,"","restrict_targets"],[12,4,1,"","ssf_parameters"],[12,4,1,"","target_type"],[12,4,1,"","tpcf_parameters"]],"mala.common.physical_data":[[13,2,1,"","PhysicalData"]],"mala.common.physical_data.PhysicalData":[[13,2,1,"","SkipArrayWriting"],[13,5,1,"","data_name"],[13,5,1,"","feature_size"],[13,3,1,"","read_dimensions_from_numpy_file"],[13,3,1,"","read_dimensions_from_openpmd_file"],[13,3,1,"","read_from_numpy_file"],[13,3,1,"","read_from_openpmd_file"],[13,5,1,"","si_dimension"],[13,5,1,"","si_unit_conversion"],[13,3,1,"","write_to_numpy_file"],[13,3,1,"","write_to_openpmd_file"],[13,3,1,"","write_to_openpmd_iteration"]],"mala.datageneration":[[15,0,0,"-","ofdft_initializer"],[16,0,0,"-","trajectory_analyzer"]],"mala.datageneration.ofdft_initializer":[[15,2,1,"","OFDFTInitializer"]],"mala.datageneration.ofdft_initializer.OFDFTInitializer":[[15,3,1,"","get_equilibrated_configuration"]],"mala.datageneration.trajectory_analyzer":[[16,2,1,"","TrajectoryAnalyzer"]],"mala.datageneration.trajectory_analyzer.TrajectoryAnalyzer":[[16,5,1,"","first_snapshot"],[16,3,1,"","get_first_snapshot"],[16,3,1,"","get_snapshot_correlation_cutoff"],[16,3,1,"","get_uncorrelated_snapshots"],[16,5,1,"","snapshot_correlation_cutoff"],[16,5,1,"","trajectory"],[16,3,1,"","uncache_properties"]],"mala.datahandling":[[18,0,0,"-","data_converter"],[19,0,0,"-","data_handler"],[20,0,0,"-","data_handler_base"],[21,0,0,"-","data_repo"],[22,0,0,"-","data_scaler"],[23,0,0,"-","data_shuffler"],[24,0,0,"-","fast_tensor_dataset"],[25,0,0,"-","lazy_load_dataset"],[26,0,0,"-","lazy_load_dataset_single"],[27,0,0,"-","multi_lazy_load_data_loader"],[28,0,0,"-","snapshot"]],"mala.datahandling.data_converter":[[18,2,1,"","DataConverter"]],"mala.datahandling.data_converter.DataConverter":[[18,3,1,"","add_snapshot"],[18,3,1,"","convert_snapshots"],[18,4,1,"","descriptor_calculator"],[18,4,1,"","target_calculator"]],"mala.datahandling.data_handler":[[19,2,1,"","DataHandler"]],"mala.datahandling.data_handler.DataHandler":[[19,3,1,"","clear_data"],[19,3,1,"","get_snapshot_calculation_output"],[19,3,1,"","get_test_input_gradient"],[19,3,1,"","mix_datasets"],[19,3,1,"","prepare_data"],[19,3,1,"","prepare_for_testing"],[19,3,1,"","raw_numpy_to_converted_scaled_tensor"],[19,3,1,"","resize_snapshots_for_debugging"]],"mala.datahandling.data_handler_base":[[20,2,1,"","DataHandlerBase"]],"mala.datahandling.data_handler_base.DataHandlerBase":[[20,3,1,"","add_snapshot"],[20,3,1,"","clear_data"],[20,5,1,"","input_dimension"],[20,5,1,"","output_dimension"]],"mala.datahandling.data_scaler":[[22,2,1,"","DataScaler"]],"mala.datahandling.data_scaler.DataScaler":[[22,3,1,"","finish_incremental_fitting"],[22,3,1,"","fit"],[22,3,1,"","incremental_fit"],[22,3,1,"","inverse_transform"],[22,3,1,"","load_from_file"],[22,3,1,"","save"],[22,3,1,"","start_incremental_fitting"],[22,3,1,"","transform"]],"mala.datahandling.data_shuffler":[[23,2,1,"","DataShuffler"]],"mala.datahandling.data_shuffler.DataShuffler":[[23,3,1,"","add_snapshot"],[23,3,1,"","shuffle_snapshots"]],"mala.datahandling.fast_tensor_dataset":[[24,2,1,"","FastTensorDataset"]],"mala.datahandling.fast_tensor_dataset.FastTensorDataset":[[24,3,1,"","shuffle"]],"mala.datahandling.lazy_load_dataset":[[25,2,1,"","LazyLoadDataset"]],"mala.datahandling.lazy_load_dataset.LazyLoadDataset":[[25,3,1,"","add_snapshot_to_dataset"],[25,3,1,"","get_new_data"],[25,3,1,"","mix_datasets"],[25,5,1,"","return_outputs_directly"]],"mala.datahandling.lazy_load_dataset_single":[[26,2,1,"","LazyLoadDatasetSingle"]],"mala.datahandling.lazy_load_dataset_single.LazyLoadDatasetSingle":[[26,3,1,"","allocate_shared_mem"],[26,3,1,"","deallocate_shared_mem"],[26,3,1,"","delete_data"],[26,3,1,"","mix_datasets"]],"mala.datahandling.multi_lazy_load_data_loader":[[27,2,1,"","MultiLazyLoadDataLoader"]],"mala.datahandling.multi_lazy_load_data_loader.MultiLazyLoadDataLoader":[[27,3,1,"","cleanup"],[27,3,1,"","load_snapshot_to_shm"]],"mala.datahandling.snapshot":[[28,2,1,"","Snapshot"]],"mala.datahandling.snapshot.Snapshot":[[28,3,1,"","from_json"]],"mala.descriptors":[[30,0,0,"-","atomic_density"],[31,0,0,"-","bispectrum"],[32,0,0,"-","descriptor"],[33,0,0,"-","lammps_utils"],[34,0,0,"-","minterpy_descriptors"]],"mala.descriptors.atomic_density":[[30,2,1,"","AtomicDensity"]],"mala.descriptors.atomic_density.AtomicDensity":[[30,3,1,"","backconvert_units"],[30,3,1,"","convert_units"],[30,5,1,"","data_name"],[30,5,1,"","feature_size"],[30,3,1,"","get_optimal_sigma"]],"mala.descriptors.bispectrum":[[31,2,1,"","Bispectrum"]],"mala.descriptors.bispectrum.Bispectrum":[[31,3,1,"","backconvert_units"],[31,3,1,"","convert_units"],[31,5,1,"","data_name"],[31,5,1,"","feature_size"]],"mala.descriptors.descriptor":[[32,2,1,"","Descriptor"]],"mala.descriptors.descriptor.Descriptor":[[32,3,1,"","backconvert_units"],[32,3,1,"","calculate_from_atoms"],[32,3,1,"","calculate_from_qe_out"],[32,3,1,"","convert_local_to_3d"],[32,3,1,"","convert_units"],[32,5,1,"","descriptors_contain_xyz"],[32,3,1,"","enforce_pbc"],[32,3,1,"","gather_descriptors"],[32,5,1,"","si_dimension"],[32,5,1,"","si_unit_conversion"]],"mala.descriptors.lammps_utils":[[33,1,1,"","extract_compute_np"],[33,1,1,"","set_cmdlinevars"]],"mala.descriptors.minterpy_descriptors":[[34,2,1,"","MinterpyDescriptors"]],"mala.descriptors.minterpy_descriptors.MinterpyDescriptors":[[34,3,1,"","backconvert_units"],[34,3,1,"","convert_units"],[34,5,1,"","data_name"],[34,5,1,"","feature_size"]],"mala.interfaces":[[36,0,0,"-","ase_calculator"]],"mala.interfaces.ase_calculator":[[36,2,1,"","MALA"]],"mala.interfaces.ase_calculator.MALA":[[36,3,1,"","calculate"],[36,3,1,"","calculate_properties"],[36,4,1,"","implemented_properties"],[36,3,1,"","load_model"],[36,3,1,"","save_calculator"]],"mala.network":[[38,0,0,"-","acsd_analyzer"],[39,0,0,"-","hyper_opt"],[40,0,0,"-","hyper_opt_naswot"],[41,0,0,"-","hyper_opt_oat"],[42,0,0,"-","hyper_opt_optuna"],[43,0,0,"-","hyperparameter"],[44,0,0,"-","hyperparameter_acsd"],[45,0,0,"-","hyperparameter_naswot"],[46,0,0,"-","hyperparameter_oat"],[47,0,0,"-","hyperparameter_optuna"],[48,0,0,"-","multi_training_pruner"],[49,0,0,"-","naswot_pruner"],[50,0,0,"-","network"],[51,0,0,"-","objective_base"],[52,0,0,"-","objective_naswot"],[53,0,0,"-","predictor"],[54,0,0,"-","runner"],[55,0,0,"-","tester"],[56,0,0,"-","trainer"]],"mala.network.acsd_analyzer":[[38,2,1,"","ACSDAnalyzer"]],"mala.network.acsd_analyzer.ACSDAnalyzer":[[38,3,1,"","add_hyperparameter"],[38,3,1,"","add_snapshot"],[38,3,1,"","perform_study"],[38,3,1,"","set_optimal_parameters"]],"mala.network.hyper_opt":[[39,2,1,"","HyperOpt"]],"mala.network.hyper_opt.HyperOpt":[[39,3,1,"","add_hyperparameter"],[39,3,1,"","checkpoint_exists"],[39,3,1,"","clear_hyperparameters"],[39,3,1,"","perform_study"],[39,3,1,"","set_optimal_parameters"],[39,3,1,"","set_parameters"]],"mala.network.hyper_opt_naswot":[[40,2,1,"","HyperOptNASWOT"]],"mala.network.hyper_opt_naswot.HyperOptNASWOT":[[40,3,1,"","get_best_trial_results"],[40,3,1,"","perform_study"],[40,3,1,"","set_optimal_parameters"]],"mala.network.hyper_opt_oat":[[41,2,1,"","HyperOptOAT"]],"mala.network.hyper_opt_oat.HyperOptOAT":[[41,3,1,"","add_hyperparameter"],[41,3,1,"","get_best_trial_results"],[41,3,1,"","get_optimal_parameters"],[41,3,1,"","get_orthogonal_array"],[41,3,1,"","load_from_file"],[41,3,1,"","number_of_runs"],[41,3,1,"","perform_study"],[41,3,1,"","resume_checkpoint"],[41,3,1,"","set_optimal_parameters"],[41,3,1,"","show_order_of_importance"]],"mala.network.hyper_opt_optuna":[[42,2,1,"","HyperOptOptuna"]],"mala.network.hyper_opt_optuna.HyperOptOptuna":[[42,3,1,"","get_trials_from_study"],[42,3,1,"","load_from_file"],[42,3,1,"","perform_study"],[42,3,1,"","requeue_zombie_trials"],[42,3,1,"","resume_checkpoint"],[42,3,1,"","set_optimal_parameters"]],"mala.network.hyperparameter":[[43,2,1,"","Hyperparameter"]],"mala.network.hyperparameter_acsd":[[44,2,1,"","HyperparameterACSD"]],"mala.network.hyperparameter_naswot":[[45,2,1,"","HyperparameterNASWOT"]],"mala.network.hyperparameter_oat":[[46,2,1,"","HyperparameterOAT"]],"mala.network.hyperparameter_oat.HyperparameterOAT":[[46,3,1,"","get_categorical"],[46,3,1,"","get_parameter"],[46,5,1,"","num_choices"]],"mala.network.hyperparameter_optuna":[[47,2,1,"","HyperparameterOptuna"]],"mala.network.hyperparameter_optuna.HyperparameterOptuna":[[47,3,1,"","get_categorical"],[47,3,1,"","get_float"],[47,3,1,"","get_int"],[47,3,1,"","get_parameter"]],"mala.network.multi_training_pruner":[[48,2,1,"","MultiTrainingPruner"]],"mala.network.multi_training_pruner.MultiTrainingPruner":[[48,3,1,"","prune"]],"mala.network.naswot_pruner":[[49,2,1,"","NASWOTPruner"]],"mala.network.naswot_pruner.NASWOTPruner":[[49,3,1,"","prune"]],"mala.network.network":[[50,2,1,"","FeedForwardNet"],[50,2,1,"","GRU"],[50,2,1,"","LSTM"],[50,2,1,"","Network"],[50,2,1,"","PositionalEncoding"],[50,2,1,"","TransformerNet"]],"mala.network.network.FeedForwardNet":[[50,3,1,"","forward"]],"mala.network.network.GRU":[[50,3,1,"","forward"],[50,3,1,"","init_hidden"]],"mala.network.network.LSTM":[[50,3,1,"","forward"],[50,3,1,"","init_hidden"]],"mala.network.network.Network":[[50,3,1,"","calculate_loss"],[50,3,1,"","do_prediction"],[50,3,1,"","forward"],[50,3,1,"","load_from_file"],[50,3,1,"","save_network"]],"mala.network.network.PositionalEncoding":[[50,3,1,"","forward"]],"mala.network.network.TransformerNet":[[50,3,1,"","forward"],[50,3,1,"","generate_square_subsequent_mask"],[50,3,1,"","init_weights"]],"mala.network.objective_base":[[51,2,1,"","ObjectiveBase"]],"mala.network.objective_base.ObjectiveBase":[[51,3,1,"","parse_trial"],[51,3,1,"","parse_trial_oat"],[51,3,1,"","parse_trial_optuna"]],"mala.network.objective_naswot":[[52,2,1,"","ObjectiveNASWOT"]],"mala.network.predictor":[[53,2,1,"","Predictor"]],"mala.network.predictor.Predictor":[[53,3,1,"","predict_for_atoms"],[53,3,1,"","predict_from_qeout"]],"mala.network.runner":[[54,2,1,"","Runner"]],"mala.network.runner.Runner":[[54,3,1,"","load_run"],[54,3,1,"","run_exists"],[54,3,1,"","save_run"]],"mala.network.tester":[[55,2,1,"","Tester"]],"mala.network.tester.Tester":[[55,3,1,"","predict_targets"],[55,3,1,"","test_all_snapshots"],[55,3,1,"","test_snapshot"]],"mala.network.trainer":[[56,2,1,"","Trainer"]],"mala.network.trainer.Trainer":[[56,3,1,"","load_run"],[56,3,1,"","run_exists"],[56,3,1,"","train_network"]],"mala.targets":[[58,0,0,"-","atomic_force"],[59,0,0,"-","calculation_helpers"],[60,0,0,"-","cube_parser"],[61,0,0,"-","density"],[62,0,0,"-","dos"],[63,0,0,"-","ldos"],[64,0,0,"-","target"],[65,0,0,"-","xsf_parser"]],"mala.targets.atomic_force":[[58,2,1,"","AtomicForce"]],"mala.targets.atomic_force.AtomicForce":[[58,3,1,"","convert_units"],[58,3,1,"","get_feature_size"]],"mala.targets.calculation_helpers":[[59,1,1,"","analytical_integration"],[59,1,1,"","entropy_multiplicator"],[59,1,1,"","fermi_function"],[59,1,1,"","gaussians"],[59,1,1,"","get_beta"],[59,1,1,"","get_f0_value"],[59,1,1,"","get_f1_value"],[59,1,1,"","get_f2_value"],[59,1,1,"","get_s0_value"],[59,1,1,"","get_s1_value"],[59,1,1,"","integrate_values_on_spacing"]],"mala.targets.cube_parser":[[60,2,1,"","CubeFile"],[60,1,1,"","read_cube"],[60,1,1,"","read_imcube"],[60,1,1,"","write_cube"],[60,1,1,"","write_imcube"]],"mala.targets.cube_parser.CubeFile":[[60,3,1,"","readline"]],"mala.targets.density":[[61,2,1,"","Density"]],"mala.targets.density.Density":[[61,3,1,"","backconvert_units"],[61,3,1,"","convert_units"],[61,5,1,"","data_name"],[61,5,1,"","density"],[61,5,1,"","feature_size"],[61,3,1,"","from_cube_file"],[61,3,1,"","from_ldos_calculator"],[61,3,1,"","from_numpy_array"],[61,3,1,"","from_numpy_file"],[61,3,1,"","from_openpmd_file"],[61,3,1,"","from_xsf_file"],[61,3,1,"","get_atomic_forces"],[61,3,1,"","get_density"],[61,3,1,"","get_energy_contributions"],[61,3,1,"","get_number_of_electrons"],[61,3,1,"","get_scaled_positions_for_qe"],[61,3,1,"","get_target"],[61,3,1,"","invalidate_target"],[61,5,1,"","number_of_electrons"],[61,3,1,"","read_from_array"],[61,3,1,"","read_from_cube"],[61,3,1,"","read_from_xsf"],[61,5,1,"","si_dimension"],[61,5,1,"","si_unit_conversion"],[61,4,1,"","te_mutex"],[61,5,1,"","total_energy_contributions"],[61,3,1,"","uncache_properties"],[61,3,1,"","write_to_cube"],[61,3,1,"","write_to_openpmd_file"]],"mala.targets.dos":[[62,2,1,"","DOS"]],"mala.targets.dos.DOS":[[62,3,1,"","backconvert_units"],[62,5,1,"","band_energy"],[62,3,1,"","convert_units"],[62,5,1,"","data_name"],[62,5,1,"","density_of_states"],[62,5,1,"","energy_grid"],[62,5,1,"","entropy_contribution"],[62,5,1,"","feature_size"],[62,5,1,"","fermi_energy"],[62,3,1,"","from_ldos_calculator"],[62,3,1,"","from_numpy_array"],[62,3,1,"","from_numpy_file"],[62,3,1,"","from_qe_dos_txt"],[62,3,1,"","from_qe_out"],[62,3,1,"","get_band_energy"],[62,3,1,"","get_density_of_states"],[62,3,1,"","get_energy_grid"],[62,3,1,"","get_entropy_contribution"],[62,3,1,"","get_number_of_electrons"],[62,3,1,"","get_self_consistent_fermi_energy"],[62,3,1,"","get_target"],[62,3,1,"","invalidate_target"],[62,5,1,"","number_of_electrons"],[62,3,1,"","read_from_array"],[62,3,1,"","read_from_qe_dos_txt"],[62,3,1,"","read_from_qe_out"],[62,5,1,"","si_dimension"],[62,5,1,"","si_unit_conversion"],[62,3,1,"","uncache_properties"]],"mala.targets.ldos":[[63,2,1,"","LDOS"]],"mala.targets.ldos.LDOS":[[63,3,1,"","backconvert_units"],[63,5,1,"","band_energy"],[63,3,1,"","convert_units"],[63,5,1,"","data_name"],[63,5,1,"","density"],[63,5,1,"","density_of_states"],[63,5,1,"","energy_grid"],[63,5,1,"","entropy_contribution"],[63,5,1,"","feature_size"],[63,5,1,"","fermi_energy"],[63,3,1,"","from_cube_file"],[63,3,1,"","from_numpy_array"],[63,3,1,"","from_numpy_file"],[63,3,1,"","from_openpmd_file"],[63,3,1,"","from_xsf_file"],[63,3,1,"","get_atomic_forces"],[63,3,1,"","get_band_energy"],[63,3,1,"","get_density"],[63,3,1,"","get_density_of_states"],[63,3,1,"","get_energy_grid"],[63,3,1,"","get_entropy_contribution"],[63,3,1,"","get_number_of_electrons"],[63,3,1,"","get_self_consistent_fermi_energy"],[63,3,1,"","get_target"],[63,3,1,"","get_total_energy"],[63,3,1,"","invalidate_target"],[63,5,1,"","local_density_of_states"],[63,5,1,"","number_of_electrons"],[63,3,1,"","read_from_array"],[63,3,1,"","read_from_cube"],[63,3,1,"","read_from_xsf"],[63,5,1,"","si_dimension"],[63,5,1,"","si_unit_conversion"],[63,5,1,"","total_energy"],[63,3,1,"","uncache_properties"]],"mala.targets.target":[[64,2,1,"","Target"]],"mala.targets.target.Target":[[64,3,1,"","backconvert_units"],[64,3,1,"","convert_units"],[64,5,1,"","feature_size"],[64,3,1,"","get_energy_grid"],[64,3,1,"","get_radial_distribution_function"],[64,3,1,"","get_real_space_grid"],[64,3,1,"","get_static_structure_factor"],[64,3,1,"","get_target"],[64,3,1,"","get_three_particle_correlation_function"],[64,3,1,"","invalidate_target"],[64,5,1,"","qe_input_data"],[64,3,1,"","radial_distribution_function_from_atoms"],[64,3,1,"","read_additional_calculation_data"],[64,3,1,"","restrict_data"],[64,5,1,"","si_dimension"],[64,5,1,"","si_unit_conversion"],[64,3,1,"","static_structure_factor_from_atoms"],[64,3,1,"","three_particle_correlation_function_from_atoms"],[64,3,1,"","write_additional_calculation_data"],[64,3,1,"","write_tem_input_file"],[64,3,1,"","write_to_numpy_file"],[64,3,1,"","write_to_openpmd_file"]],"mala.targets.xsf_parser":[[65,1,1,"","read_xsf"]],mala:[[8,0,0,"-","common"],[14,0,0,"-","datageneration"],[17,0,0,"-","datahandling"],[29,0,0,"-","descriptors"],[35,0,0,"-","interfaces"],[37,0,0,"-","network"],[57,0,0,"-","targets"],[66,0,0,"-","version"]]},objnames:{"0":["py","module","Python module"],"1":["py","function","Python function"],"2":["py","class","Python class"],"3":["py","method","Python method"],"4":["py","attribute","Python attribute"],"5":["py","property","Python property"]},objtypes:{"0":"py:module","1":"py:function","2":"py:class","3":"py:method","4":"py:attribute","5":"py:property"},terms:{"0":[2,5,6,11,12,13,18,22,32,33,36,39,43,44,45,46,47,53,59,61,63,64,69,72,76],"000":[2,74],"00001":72,"0048450":64,"005":69,"01":69,"01070":73,"015":69,"023":73,"030":41,"035120":73,"03610":64,"045008":73,"05":12,"1":[2,5,6,12,20,22,32,36,58,59,60,61,62,63,64,70,72,73],"10":[2,3,12,38,41,64,70,72,73,76],"100":[2,6,12,72,74],"1007":41,"1038":73,"104":73,"1063":64,"108":73,"1088":[38,73],"11":[6,12,70,72],"1103":73,"115":73,"12":[3,5,73],"1234":6,"125146":73,"16":73,"1606":64,"1696":64,"17":[64,73],"1883":12,"1_31":41,"1d":[61,63],"1s":12,"2":[2,5,6,12,33,59,62,64,70,72,77],"20":69,"200":5,"2017":60,"2019":[11,60],"2021":73,"2022":73,"2023":73,"2153":[38,73],"224":5,"25th":60,"2632":[38,73],"2685":12,"27":73,"2mic":64,"3":[2,3,12,20,32,41,61,63,70,73,76],"32":[59,69],"33":59,"36808":41,"39m":77,"3d":[61,63],"4":[2,6,12,13,18,70,72,73,76],"40":72,"400":5,"5":[3,6,12,64,70,72],"500":5,"57":64,"6":64,"64":69,"67637":[70,72],"7":[70,76,77],"8":[12,75],"9":73,"91":[32,70],"94":32,"96":69,"97":32,"978":41,"abstract":[13,39,50,64,73],"boolean":[48,49],"break":32,"case":[6,11,12,13,25,26,41,42,48,53,54,63,64,69,75,77],"class":[0,2,4,5,6,10,11,12,13,15,16,18,19,20,22,23,24,25,26,27,28,29,30,31,32,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,58,60,61,62,63,64,69,70,71,72],"const":60,"default":[4,5,6,11,12,18,19,28,32,33,38,52,53,54,56,62,63,69,70,77],"do":[0,2,3,4,5,7,11,12,19,20,23,25,26,27,30,31,32,34,41,42,50,55,57,59,60,61,63,67,69,70,71,72,75,78],"export":[10,12,76,77],"final":[6,11,72],"float":[12,16,30,33,39,43,44,45,46,47,50,53,59,60,62,63,64,69],"function":[0,1,2,3,5,6,8,9,11,12,13,16,17,22,28,30,31,32,33,34,36,41,42,43,49,50,51,52,58,59,61,62,63,64,69,70,71,72,73,74,76,78],"import":[1,2,3,36,41,53,63,64,71,77,78],"int":[11,12,13,15,16,18,19,23,25,26,39,43,44,45,46,47,50,52,55,59,60,61,62,64,69],"long":[6,12],"new":[0,3,6,11,12,23,25,26,33,69,72],"p\u00f6schel":0,"public":[2,3,6,69,70,73],"return":[2,10,11,12,13,16,19,22,28,30,31,32,33,34,39,41,42,43,46,47,48,49,50,53,54,55,56,58,59,60,61,62,63,64,65],"static":[5,12,27,30,31,32,34,42,50,58,60,61,62,63,64],"switch":[2,5,12],"true":[2,3,5,6,12,13,18,19,22,25,26,32,33,39,41,42,53,54,56,59,61,62,63,64,70,72],"try":26,"var":21,"while":[2,6,12,61,63,64,73],A:[0,3,5,6,10,11,12,13,16,20,24,27,28,32,36,40,42,48,49,51,53,55,56,60,61,63,64,69,73,74],AND:[11,42,50,60],AS:[11,60],ASE:[5,13,30,32,36,53,61,62,63,64],As:[2,3,4,5,62,72,76,78],BE:[11,42,60],BUT:[11,60],Be:[6,12,50],By:[0,5,6,11,12,61,62,63,69,70,72],FOR:[11,60],For:[2,3,4,5,12,16,19,26,32,36,42,54,56,63,64,69,70,71,72,74,75,78],IN:[11,60],IS:[11,60],IT:42,If:[0,2,3,4,5,6,12,13,15,16,18,19,20,22,23,25,26,32,33,38,39,41,42,48,49,53,54,55,56,59,60,61,62,63,64,69,70,73,74,75,77],In:[0,2,6,12,13,25,39,42,43,44,45,46,47,48,61,62,63,64,69,70,71,72,75,77],It:[3,6,12,26,53,55,60,61,62,63,64,68,71,72,74],NO:[11,60],NOT:[11,12,42,60],No:[2,6,12,22,36,72],OF:[11,12,15,60,74],OR:[11,60],Of:[6,12,72],On:3,One:[3,5,6,60,69,72],THE:[11,42,60],THEN:42,TO:[4,11,42,60],That:[54,69],The:[0,1,2,3,4,5,6,10,11,12,13,16,18,19,28,30,32,33,38,39,40,41,42,50,52,54,56,59,60,61,62,63,64,65,68,69,70,71,72,73,74,75,76,77,78],Their:70,Then:[2,5],There:[2,62,69,72],These:[2,3,6,18,42,62,69,70,74],To:[2,4,5,6,12,26,50,72,73,74,75,77],WILL:42,WITH:[11,60],Will:[16,33,43,63],With:[5,12,25,36,69],__getitem__:24,_build:76,_xxx:12,ab:64,abc:[13,20,39],abil:6,abl:0,about:[5,60,64],abov:[2,11,12,16,49,60,72],absolut:[50,55],absolute_valu:12,ac9956:[38,73],acceler:[1,3,5,6,68,73,74],acces:61,access:[3,5,6,9,16,21,22,26,36,64,69,70,71,72,74,77,78],accompani:[0,72,78],accord:[2,61,64,69],accordingli:[70,74],account:[64,74],accur:[2,3,6,64,70],accuraci:[3,6,12,41,72],achiev:12,acitv:12,acquaint:74,acquir:71,across:[1,12,55,72,73,74],acsd:[2,38,70],acsd_analyz:[7,37,67],acsd_point:2,acsdanalyz:[2,38],action:[11,12,60],activ:[0,3,4,5,6,12,54,69,72,74],actual:[0,6,13,16,25,41,42,50,55,69,72,78],actual_output:55,ad:[6,12,16,20,22,25,33,69,70],adam:[0,12,72],add:[0,2,12,18,20,22,23,25,33,38,39,41,69,70,72,73,75,77],add_hyperparamet:[2,38,39,41,69],add_snapshot:[2,4,6,18,20,23,38,69,70,72],add_snapshot_a:20,add_snapshot_to_dataset:25,addit:[0,5,6,12,13,18,36,54,61,64,73,76],addition:[6,72,74],additional_attribut:[13,61,64],additional_calculation_data:[54,72],additional_info_input_:70,additional_info_input_path:[18,70],additional_info_input_typ:[18,70],additional_info_save_path:[18,23,70],additional_metadata:13,additon:[12,36],aditya95sriram:60,adjust:[5,12,64,69,71],adress:[12,42],advanc:[2,5,68,69,70,71,72,73,74,76],advantag:18,advers:6,advis:[2,5,12,54],affect:[6,18],aforement:3,after:[0,3,6,12,36,70,72,75,76],after_before_training_metr:[3,6,12],afterward:[2,6,25,62,71,72],again:[22,76],against:[48,49],aggres:12,agre:[0,72],aidan:[0,73],aim:[5,6],akin:6,al:42,algorihm:12,algorithm:[6,12,69,74],all:[0,1,2,3,4,5,6,10,11,12,13,16,17,18,19,20,22,23,25,26,28,32,36,39,42,43,51,53,54,55,59,60,61,62,63,64,68,69,70,71,72,76,77,78],all_chang:36,alloc:[2,12,26],allocate_shared_mem:26,allow:[0,4,5,6,12,72,74,76],allreduc:12,along:[5,59,73,74],alongsid:[4,13,61,63,76],alphabet:0,alreadi:[6,13,54,71,72,76],also:[1,2,4,5,6,10,12,19,41,50,54,68,70,71,72,73,76,78],alter:[3,71],altern:[12,13,42],alternative_storage_path:42,although:[40,61,74],aluminium:74,alwai:[6,11,12,38,39,43,44,45,46,47,63,68,69,70,75],am:32,american:73,among:69,amount:[2,6,23,72],amp:12,an:[0,1,2,3,4,5,6,11,12,13,15,16,19,25,26,28,30,32,33,36,41,42,44,46,47,48,49,50,51,53,54,58,60,61,62,63,64,68,69,70,71,74,75,76,77],analys:40,analysi:[2,4,5,12,16,38,41,42],analyt:[59,62,63],analytical_integr:59,analyz:[16,38],ang:[58,61],angstrom:32,ani:[0,6,11,12,13,16,18,24,25,26,36,48,49,50,60,61,64,69,70,72,73,74],anoth:[3,6,26],anyth:[12,61],anywai:18,ap:73,apart:[6,70],api:[4,71,72,74],apidoc:76,appli:[12,19,22,42,64,72,73],applic:[42,52],approach:[18,25,26,28,39,43,44,45,46,47,73],appropri:[0,6,63,70],approxim:59,apt:77,ar:[0,1,2,3,4,5,6,11,12,13,16,18,19,20,25,26,28,32,39,40,42,43,44,45,46,47,50,52,53,54,55,58,59,60,61,62,63,64,65,68,69,70,71,72,73,74,76,78],arbitrari:64,architectur:[3,37,39,40,42,50,51,69,75,76],archiv:[16,72],arg:[24,25,26,36,48,49,50,60],argdict:33,argument:[12,18,33,59,70],aris:[11,60,77],around:2,arrai:[3,12,13,18,19,20,22,23,27,28,30,31,32,33,34,41,46,50,51,53,58,59,60,61,62,63,64,65,76],array_shap:33,articl:[73,74],arxiv:64,as_numpi:22,asap3:64,asap:64,ase:[15,16,30,32,36,53,61,63,64,71],ase_calcul:[7,35,67],aspect:72,assert:74,assign:[6,12,50],associ:[11,60,61,62],assum:[12,13,16,25,26,33,50,59,61,64,68,69,72,77],assumpt:12,asterisk:63,atom:[2,5,6,12,15,16,28,32,36,53,58,60,61,63,64,70,71,72,74,78],atomic_dens:[7,29,67],atomic_density_sigma:12,atomic_forc:[7,57,61,67],atomicdens:30,atomicforc:58,atomist:71,atoms_angstrom:[61,63,64],attach:6,attempt:[4,23,54,56,61,63,64],attent:[12,73],attila:[0,73,74],attribut:[10,12,13,16,21,28,51,61,64],austin:[0,73],author:[11,60,73],automat:[0,3,5,6,12,16,41,50,64,76],avail:[0,2,6,9,12,18,32,39,43,44,45,46,47,59,69,70,72,75,76],availab:6,averag:[2,3,12,64,72],avoid:[3,12,26],awar:[5,50,64,75,77],axi:[12,59],b:[59,73,74],back:[12,26,42],backbon:72,backconvert_unit:[30,31,32,34,61,62,63,64],backend:[5,12],background:3,bad:6,band:[6,12,48,55,62,63,72],band_energi:[3,6,12,48,55,62,63,72],band_energy_ful:55,barrier:11,bartosz:0,base:[0,2,3,4,5,10,12,13,15,16,18,19,20,22,23,24,25,26,27,28,30,31,32,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,58,60,61,62,63,64,69,72,74],baselin:11,baseprun:[48,49],basi:[12,60],basic:[2,5,6,68,70,72,74],bat:76,batch:[12,52,69],batch_siz:52,be_dens:5,be_ldo:70,be_model:[71,72],be_shuffl:[4,6],be_snapshot0:[4,6,70,72],be_snapshot1:[2,6,71,72],be_snapshot2:2,be_snapshot:[4,70],becaus:[3,12,36,72],been:[0,2,3,6,22,32,62,70,72,73,74,76,77,78],befor:[0,6,12,48,49,63,64,72,76],behavior:12,being:[5,6,11,25,26,36,54,55,56,61,62,63,72],believ:12,below:[0,12,16,60],benchmark:54,best:[12,40,41,61,69],beta:[59,62],better:6,between:[2,3,6,11,12,16,23,25,42,69],bias:[6,12],bidirect:12,big:[0,64],bigger:12,bin:[12,64,75,77],binari:[70,76],bind:77,bispectrum:[2,7,12,29,32,67,70,71,72,75],bispectrum_cutoff:[2,12,70,72],bispectrum_switchflag:12,bispectrum_twojmax:[2,12,70,72],bit:[12,24,61],black:0,blob:[11,64],bohr:[2,61,63,70],boldsymbol:63,bool:[11,12,13,18,19,22,25,26,32,33,39,41,42,48,49,53,54,56,59,61,62,63,64],both:[2,3,55,60,74],bottleneck:6,bound:[39,43,44,45,47,69],boundari:12,bp:4,branch:75,briefli:6,brillouin:59,broadcast_band_energi:62,broadcast_entropi:62,broadcast_fermi_energi:62,brown:11,brzoza:0,buffer:[26,27],bug:0,bugfix:0,build:[0,4,12,19,68,74],build_fold:75,build_mpi:75,build_shared_lib:75,build_total_energy_energy_modul:77,built:[0,11,75],bump2vers:76,bumpvers:0,busi:6,by_snapshot:12,c:[11,60,64],cach:[16,25,26,61,62,63,64],calcul:[0,2,5,6,11,12,13,15,16,18,19,20,22,28,29,30,31,32,33,34,36,38,41,50,52,53,54,55,57,58,59,61,62,63,64,69,70,72,73,74,75,78],calculate_from_atom:32,calculate_from_qe_out:32,calculate_loss:50,calculate_properti:36,calculation_help:[7,57,67],calculation_output:[19,28],calculation_output_fil:20,calculation_typ:64,calibr:[48,49],call:[2,3,6,11,12,13,16,18,24,41,42,49,50,62,64,70,71,72,73,74,78],callow:0,can:[0,2,3,4,5,6,7,9,10,11,12,13,16,18,19,22,25,26,32,36,41,42,50,51,53,54,55,56,64,69,70,71,72,74,75,77,78],candid:[48,49,69],cangi:[0,73,74],cannot:[6,32,61,63],capabilit:2,capabl:[1,3,4,74],care:[6,26,42],categor:[3,12,39,41,43,44,45,46,47,69],categori:11,caus:73,cd:76,cell:[5,12,30,32,36,50,61,63,64],center:[59,74],cento:78,central:[3,50,72],certain:[12,18,39,40,42,62],cff:0,cflag:77,challeng:[73,74],chanc:[3,12],chang:[0,3,4,5,12,36,62,64,75,76,77],changelog:0,chapter:41,character:[12,30],charg:[11,36,60],check:[0,4,6,9,19,22,36,39,48,54,56,75,76],check_modul:[7,8,67],checkout:[21,75,76],checkpoint:[12,36,39,41,42,54,56],checkpoint_exist:[39,56],checkpoint_nam:[3,6,12,39,41,42],checkpoints_each_epoch:[6,12],checkpoints_each_tri:[3,12],chemistri:73,choic:[38,39,41,43,44,45,46,47,52,69,72],choos:[0,2,12],chosen:[2,12,70],ci:0,circumv:[6,73],citat:[0,73],cite:74,citeseerx:64,cl:54,claim:[11,60],classic:36,classmethod:[10,12,22,28,36,39,41,42,50,54,56,61,62,63],clean:[42,76],cleanup:27,clear:[0,19,39],clear_data:[19,20],clear_hyperparamet:39,clone:76,cloud:2,cluster:[3,42,77],cmake:75,cmake_cxx_compil:75,cmdarg:33,coars:[2,72],code:[3,32,35,64,68,71,73,74,75,76,78],coeffici:72,collabor:0,collect:[3,12,33],collector:36,com:[0,11,12,21,41,60,64,75,76,77],combin:[2,32,36,69],come:[12,32],comm:[11,13],comm_world:11,command:[3,12,33,69],comment:12,commit:0,common:[7,11,12,15,16,18,19,20,23,28,30,31,32,34,36,38,39,40,41,42,43,48,49,50,52,53,54,55,56,58,61,62,63,64,67],commun:[3,11,12,32],compar:[2,12,16,72,74],comparison:64,compat:[3,4,12,21,41,42,50,51,65,71,75],compil:[75,77],complei:60,complet:[6,70],complete_save_path:[6,18,23,70],complex:60,complianc:0,compliant:4,complic:[2,6],compon:[32,70],comprehens:74,compress:[4,12],compuat:64,comput:[1,2,12,22,33,68,73,74],computation:[3,5],compute_typ:33,concept:[3,74],concern:37,concert:54,conda:0,condens:70,condit:[3,11,60],conduct:74,config:0,configur:[0,4,12,15,16,32,53,71,72,75,77],conjunct:[3,12],connect:[11,60],consecut:12,conserve_dimens:63,consid:[0,12,19],consist:[18,19,28,60,62,63,69,72,78],consquenc:16,constant:60,constitut:0,construct:[3,12,18,59,64,72,73,74],constructor:60,consult:[0,4],contain:[2,4,10,12,13,20,23,28,29,32,36,40,55,60,61,62,63,64,72],continu:[54,56,76],contract:[11,60],contribut:[12,61,62,63,74],control:[12,25,32,64,72],convent:[39,41,64],convers:[1,13,19,20,23,25,26,27,32,33,58,61,62,63,64,68],convert3dto1d:19,convert:[4,10,12,18,19,30,31,32,33,34,38,58,61,62,63,64,70],convert_local_to_3d:32,convert_snapshot:[4,18,70],convert_to_threedimension:61,convert_unit:[30,31,32,34,58,61,62,63,64],converted_arrai:[30,31,32,34,58,61,62,63,64],converted_tensor:19,convet:[43,44,45,46,47],cooper:6,coordin:[12,32],copi:[11,48,49,54,60,61,62],copyright:[11,60],core:[0,77],correct:[2,5,6,36,43,50,60,61,69,72,76],correctli:[0,61,76],correl:[3,12,16,64],correspond:[6,12,64,69,70],cosin:[2,16],cost:12,costli:74,could:[5,12],count:12,counter:12,cours:[6,12,72],cover:[68,71],covers:[61,63],cpp:64,cppflag:77,cpu:[1,2,3,6,53,54,63,68,75],cpython:77,creat:[5,6,12,13,15,16,18,19,20,23,30,31,32,34,36,38,39,40,41,42,48,49,50,52,53,54,55,56,58,60,61,62,63,64,69,70,71,72,75,76],create_fil:61,create_qe_fil:63,creation:[19,70],critic:72,crucial:4,csv:72,cube:[5,60,61,63,70],cube_pars:[7,57,67],cubefil:60,cubetool:60,cubic:[61,63,64,74],cuda:[6,12,75],current:[0,3,4,5,6,11,12,14,25,26,38,39,40,41,43,46,47,50,51,54,58,59,60,61,62,63,64,70],curv:12,custom:[63,69],cut:12,cutoff:[2,12,16,70],d:[59,62,63,73,74,75],d_model:50,dai:73,damag:[11,60],daniel:[0,11],data:[0,1,3,5,6,7,12,13,14,17,18,19,20,21,22,23,24,25,26,27,28,30,31,32,33,34,36,38,39,40,41,42,50,53,54,55,56,58,59,60,61,62,63,64,65,68,69,71,73,74,78],data_:4,data_convert:[4,7,17,38,67,70],data_handl:[4,5,7,17,36,39,40,41,42,49,51,52,53,54,55,56,63,67,69,71,72],data_handler_bas:[7,17,19,23,67],data_nam:[13,30,31,34,61,62,63],data_path:[2,4,6,70,71,72],data_repo:[7,17,67],data_repo_path:21,data_scal:[7,17,19,25,26,67],data_shuffl:[4,6,7,17,67],data_splitting_typ:12,data_typ:[19,55,64],databas:3,databasenam:3,dataconvert:[2,4,6,18,19,70],dataformat:60,datagener:[7,67],datahandl:[2,3,4,6,7,18,19,23,25,26,27,36,38,39,40,41,42,49,52,53,54,55,56,63,67,69,72],datahandlerbas:[19,20,23],dataload:[25,26],datasampl:[25,26],datascal:[19,22,25,26],dataset:[13,19,24,25,26,27],datashuffl:[4,6,12,23],datashufl:6,datatyp:[39,41,43,44,45,46,47],date:[0,12,60],dayton:73,db:63,dd:63,dd_db:63,de:63,de_dd:63,deactivt:69,dead:42,deadlin:0,deal:[11,13,60,72],dealloc:[26,27],deallocate_shared_mem:26,debian:77,debug:[3,12,72,76],decad:73,decai:12,decid:[0,12,69,72],declar:4,decreas:[12,69],deep:[73,74],defin:[12,48,49,59,62,63,71],degre:16,delete_data:26,delta:[59,62],demand:[2,3,12,50],demonstr:[73,74],denois:12,dens_object:61,denser:70,densiti:[2,5,7,12,55,57,58,62,63,67,71,73,74],density_calcul:[5,61],density_data:[61,63],density_of_st:[5,62,63,71],depend:[5,12,13,19,54,56,60,61,63,70,76],depth:[1,69],deriv:[25,26,27,50,63],descent:12,desciptor:32,describ:[13,30,31,34,61,62,63,69],descript:[0,60,69],descriptor:[0,5,7,11,12,18,19,20,23,25,26,27,28,30,31,34,38,53,63,67,70,71,72,74,75],descriptor_calcul:[18,19,20,23,25,26,27,38],descriptor_calculation_kwarg:[18,70],descriptor_dimens:32,descriptor_input_path:[18,38,70],descriptor_input_typ:[18,38,70],descriptor_save_path:[18,23,70],descriptor_typ:[12,70,72],descriptor_unit:[18,38],descriptors_contain_xyz:[12,32],descriptors_np:32,deseri:10,deserialized_object:[10,12,28],design:3,desir:[12,16,19,30,31,32,34,43,50,61,62,63,64,74],despit:73,detail:[2,3,12,18,38,74],determin:[2,3,5,12,16,55,69,70,72],determinist:12,detriment:12,dev:76,develop:[6,70,74,76,78],deviat:[3,12,22,72],devic:12,devis:2,dft:[3,5,6,7,12,15,18,22,28,32,61,62,63,68,70,74],diagnost:12,dicitionari:33,dict:[10,12,13,18,28,33,55,60,61,63,64,65],dictionari:[10,12,13,18,28,32,33,55,61,62,63,64,72],dictionati:[61,63,64],diff:0,differ:[2,5,6,38,42,52,59,61,69],differenti:12,dim:19,dimens:[5,12,13,20,25,26,30,31,32,34,50,58,61,62,63,64,72],dimension:[2,13,62,70],dipol:36,direct:[0,5,12,18,64,71],directli:[0,2,6,11,12,32,50,53,54,61,62,63,64,72],directori:[0,6,12,18,19,20,23,28,32,63,76,77],dirti:0,disabl:[6,12,25,26,54],discontinu:12,discourag:[25,26],discret:[5,61,62,63,70],discuss:[1,2,3,6,70,72,74],disentangl:3,disk:[6,23,63,72],displac:16,distanc:[2,12,16],distance_threshold:16,distinct:[2,39,43,44,45,46,47],distinguish:3,distribut:[3,5,11,12,50,60,62,64],divid:[5,61],divisor:[12,59],do_predict:50,doc:76,dockerfil:0,docstr:0,document:[0,4,11,12,60,71,78],documentari:76,doe:[6,11,12,19,30,31,34,39,40,56,60,61,62,63,69,76],doesn:[60,62],doi:[38,64,73],don:[12,64],done:[0,2,3,5,11,12,32,38,39,40,41,42,53,55,60,61,64,69,70,72],dornheim:74,dos_calcul:62,dos_data:[62,63],dos_object:62,dos_valu:63,dot:60,doubl:[18,33],doubt:32,down:11,download:77,drastic:[6,18],drawback:6,dresden:74,drive:28,driven:[4,72],dropout:[12,50],dtype:[13,60],due:[61,62,63],dummi:60,dure:[0,2,6,11,12,49,52,54,63,64,69,71,72,73,76],during_training_metr:12,dx:73,dynam:[12,55,71,74],e:[1,3,4,5,6,12,13,16,18,19,30,31,32,34,35,36,38,39,40,41,42,43,44,45,46,47,59,61,62,63,64,69,70,71,72,75,76,77,78],e_:61,e_ewald:61,e_grid:[62,63],e_hartre:61,e_rho_times_v_hxc:61,e_xc:61,eac:12,each:[0,2,3,5,12,16,42,48,49,69,70,72,74],earli:12,earlier:64,early_stopping_epoch:[12,69],early_stopping_threshold:12,easi:[3,6,55],easier:[19,71,72],easili:[0,2,3,6,69,72],edu:64,effect:[3,6,12,33,54,63,74],effici:[4,5,64,74,78],effort:[0,74],effortlessli:74,eigenvalu:62,either:[0,5,12,13,19,20,23,40,55,59,61,63,64,69,70,72],electron:[5,7,36,55,58,61,62,63,64,70,71,72,73,74],elem_snapshot:18,elimin:3,elli:[0,73,74],els:[3,6],elsewis:[13,16],emploi:[1,6,72,74],empti:[12,65],emul:22,en:41,enabl:[2,3,5,6,53,54,55,70,72,75],encapsul:6,encod:[2,32,51,70,72,78],encourag:4,end:[3,4,11,12,13,16,42,61,62,63,64,69,72],energi:[0,5,6,7,12,36,48,55,59,61,62,63,64,70,71,72,74,78],energy_grid:[5,59,62,63],energy_integration_method:63,energy_unit:59,energygrid:[62,63],enforc:[32,50,64],enforce_pbc:32,enhanc:[0,74],enough:[2,6,12,48,49,70,78],ensur:[0,6,11,12,18,19,61,63,74],enter:63,entir:[5,6,13,19,20,28,32,50,54,70,72],entri:[0,5,12,61,72],entropi:[59,62,63],entropy_contribut:[62,63],entropy_multipl:59,enviro:70,environ:[0,2],epoch:[6,12,69],epsilon:[59,62],epsilon_:62,epsilon_f:[59,62,63],eq:[59,64],equal:33,equat:[62,64],equilibr:[12,15,16,74],equilibrated_snapshot:16,equival:62,erro:76,erron:26,error:[5,6,11,12,25,55,61,62,63,76],especi:[3,12,48,78],espresso:[2,5,18,32,61,62,63,64,70,71,78],essenti:[12,18,69],establish:6,estim:[12,16],etc:[0,3,10,12,20,28,36,39,43,44,45,46,47,54,69,71,72],euclidean:12,ev:[12,20,32,58,59,61,62,63,64],evalu:[3,5,12,19,63],even:[1,5,64,71],evenli:5,event:[11,60],eventu:[36,63],everi:[0,15,63],everyth:[12,37],evid:12,ewald:61,ex01_checkpoint:6,ex01_checkpoint_train:6,ex01_train_network:72,ex02_shuffle_data:6,ex02_test_network:72,ex03_preprocess_data:70,ex03_tensor_board:6,ex04_acsd:2,ex04_hyperparameter_optim:69,ex05_checkpoint:3,ex05_checkpoint_hyperparameter_optim:3,ex05_run_predict:71,ex06_ase_calcul:71,ex06_distributed_hyperparameter_optim:3,ex07_advanced_hyperparameter_optim:3,ex08_visualize_observ:5,exact:[62,63],exactli:[61,62,63],exampl:[0,2,3,4,5,6,21,41,68,69,70,71,72,74,75],example_minimal_number_of_runs_oa:41,except:[3,5,61,64],excess:73,exclud:12,exclus:[5,69],execut:[0,3,22,42,68,75],exhibit:74,exist:[3,6,26,39,54,56,60,62,71],expans:2,expect:[6,12],experi:12,experiment:[12,14,69],experiment_ddmmyi:12,explain:69,explan:69,explicitli:[12,32],explictli:32,explor:74,exploratori:[2,4],expon:59,express:[11,60,62,63],extend:[5,18,69,71,74],extens:[4,6],extent:13,external_modul:77,extra:[0,32],extract:[3,13,33,46,47,61,65],extract_compute_np:33,f0:59,f1:59,f2:59,f2py:61,f90:77,f90exec:77,f:59,facilit:74,factor:[2,5,6,12,41,59,62,64,69],fail:12,fairli:[32,71],falkner18a:12,fals:[2,6,12,13,16,18,19,22,25,32,33,38,39,40,41,42,53,54,56,59,61,63,64],familiar:[3,68,72],far:[12,70],faruk:0,fashion:69,fast:12,fast_tensor_dataset:[7,17,67],faster:[5,6,18,24,32,71,75,77],fasttensordataset:[24,26],featur:[0,3,6,12,13,20,22,30,31,34,58,61,62,63,64,68,69,72,74,78],feature_from:13,feature_s:[13,30,31,34,61,62,63,64],feature_to:13,fed:74,feed:[12,50],feed_forward:12,feedforwardnet:50,fermi:[55,59,62,63,64],fermi_energi:[59,62,63],fermi_energy_self_consist:[62,63],fermi_funct:59,fermi_v:59,fetch:27,few:[3,5,72],feynman:61,ff:0,ff_multiple_layers_count:69,ff_multiple_layers_neuron:69,ff_neurons_lay:69,ff_neurons_layer_001:[39,43,44,45,46,47],ff_neurons_layer_002:[39,43,44,45,46,47],ff_neurons_layer_00:69,ff_neurons_layer_01:69,ff_neurons_layer_xx:69,ff_neurons_layer_xxx:12,fflag:77,fiedler:[0,73,74],field:70,file:[0,3,4,5,6,10,11,12,13,15,16,18,19,20,22,23,25,26,27,28,32,36,41,42,50,53,54,56,60,61,62,63,64,65,69,70,72,74,76,77],file_based_commun:[18,38],file_index:25,file_nam:61,file_path:[41,42],filenam:[4,12,22,36,60,65],filename_uncorrelated_snapshot:16,filepath:64,fill:[12,15,69,70],find:[0,41,73,77],fine:[6,12,70],fingerprint:[12,18,32,38],finish:[6,42],finish_incremental_fit:22,finit:[73,74],first:[2,5,12,16,18,48,49,61,69,70,71,72,74,76,78],first_snapshot:16,firstli:[2,69,72],fit:[11,22,60],fix:[0,76],flag:72,flexibl:64,fname:60,focu:74,folder:[0,12,75,76],follow:[0,1,6,11,12,39,41,43,44,45,46,47,59,60,61,68,69,71,72,74,76],footprint:[12,63],forc:[7,36,58,61,63],forgiv:12,fork:0,form:[0,12,60,61,71],formal:4,format:[5,12,13,22,32,43,52,56,60,61,62,63,64,65,70,71,72],former:1,formerli:12,formula:59,fortran:61,forward:[12,50,52],found:[3,12,38,39,40,41,42],fourier:[12,64],fourier_transform:64,fox:0,fp32:18,fpic:77,frac:[59,63],fraction:12,framework:[3,7,13,50,72],franz:0,free:[3,11,26,60,73,74,78],freedom:22,friction:12,from:[0,2,3,4,5,6,10,11,12,13,16,22,25,26,28,32,33,36,40,41,42,46,47,50,52,53,54,56,59,60,61,62,63,64,65,70,71,72,76],from_cube_fil:[61,63],from_json:[10,12,28],from_ldos_calcul:[5,61,62],from_numpy_arrai:[61,62,63],from_numpy_fil:[61,62,63],from_openpmd_fil:[61,63],from_qe_dos_txt:62,from_qe_out:62,from_xsf_fil:[61,63],front:12,frozentri:[42,48,49],full:[4,6,38,72,75,77],full_visualization_path:6,fulli:[3,4,19],function_valu:59,fundament:0,furnish:[11,60],further:[0,3,4,5,6,12,54,56,69,70,71,72,73,74,75],furthermor:[4,78],futur:[62,72],g:[3,4,5,6,12,13,16,18,30,31,32,34,35,36,39,43,44,45,46,47,61,62,63,64,69,70,71,72,73,74,75,76,77,78],gabriel:[0,73],gain:73,gather:[18,24,32,53,63,72],gather_dens:63,gather_descriptor:32,gather_do:63,gather_ldo:53,gaussian:[12,30,34,59,60],gcc:[75,77],gener:[0,2,5,6,8,11,12,13,14,16,18,41,50,61,62,63,64,68,71,72,73,77],generate_square_subsequent_mask:50,get:[5,11,12,13,19,30,31,32,34,40,41,43,46,53,55,58,59,61,62,63,64,71,72,74],get_atomic_forc:[61,63],get_band_energi:[62,63],get_best_trial_result:[40,41],get_beta:59,get_categor:[46,47],get_comm:11,get_dens:[61,63],get_density_of_st:[62,63],get_energy_contribut:61,get_energy_grid:[62,63,64],get_entropy_contribut:[62,63],get_equilibrated_configur:15,get_f0_valu:59,get_f1_valu:59,get_f2_valu:59,get_feature_s:58,get_first_snapshot:16,get_float:47,get_int:47,get_local_rank:11,get_new_data:25,get_number_of_electron:[61,62,63],get_optimal_paramet:41,get_optimal_sigma:30,get_orthogonal_arrai:41,get_paramet:[46,47],get_potential_energi:71,get_radial_distribution_funct:64,get_rank:11,get_real_space_grid:64,get_s0_valu:59,get_s1_valu:59,get_scaled_positions_for_q:61,get_self_consistent_fermi_energi:[62,63],get_siz:11,get_snapshot_calculation_output:19,get_snapshot_correlation_cutoff:16,get_static_structure_factor:64,get_target:[61,62,63,64],get_test_input_gradi:19,get_three_particle_correlation_funct:64,get_total_energi:63,get_trials_from_studi:42,get_uncorrelated_snapshot:16,git:[0,75,76],github:[0,11,12,21,73,75,76],gitlab:[64,77],give:[1,3,6,12,16,63,68,69,70,72,75],given:[0,6,13,18,32,53,56,59,60,61,62,63,64,69,70,74,78],glimps:72,gmail:60,gnn:0,gnu:77,go:12,goal:65,goe:12,goo:11,good:[2,3,6,12,48,49],got:0,govern:[69,70],gpaw:71,gpu:[0,3,11,12,54,68,75],gradient:[12,19,25,26,69],grand:73,grant:[11,60],granular:70,graph:[6,12],grate:0,greater:12,greatli:[12,72],grid:[0,5,12,30,32,59,61,62,63,64,70,72,74,78],grid_dimens:[32,61,64],grid_integration_method:63,gridi:[61,63],gridpoint:61,gridsiz:[12,61,63],gridspac:12,gridx:[61,63],gridz:[61,63],ground:72,grow:73,gru:[12,50],guarante:6,guess:64,gui:4,guid:[1,2,5,68,69,70,71,72,74],guidelin:0,h5:[4,13,61,64],h:[61,75],ha:[0,2,4,5,6,11,12,13,22,25,33,36,41,42,48,49,50,53,54,61,62,63,69,70,72,73,74,76,77,78],hacki:12,had:[6,70],hand:[5,12,13],handl:[3,4,6,17,19,20,23,64,76],handler:[41,42,54,56,63],happen:62,har:74,hard:28,hardwar:[1,5,68],haswel:75,have:[0,2,3,5,6,10,12,13,22,25,26,28,30,31,32,34,38,39,42,43,44,45,46,47,59,62,63,64,69,70,71,72,73,75,76,77,78],haven:76,head:[0,12],heartbeat:12,heavi:[5,64],hellman:61,helmholtz:74,help:[3,12,53,63,68,72],helper:[4,59],here:[3,12,16,18,25,26,38,41,50,54,62,69,70,71,72,75],herebi:[11,60],hidden:[12,50,69],hierarchi:13,high:[11,12,39,43,44,45,46,47,73],higher:[12,39,43,44,45,47],highli:[2,4,5,6,14,76,78],hint:6,histogram:[12,64],hiwonjoon:11,hlist:12,hoc:16,hoffmann:[0,73,74],hold:[6,12,19,32,39,40,41,42,53,54,55,56,63],holder:[11,60],horovod:[0,11,12,22,25,26],hossein:0,hotyp:[43,44,45,46,47],how:[2,3,12,22,62,63,64,68,69,70,72,75],howev:[2,4,6,12,26,32,52,63,72,73],hpc:[3,6,12,42,77],html:[12,41,76],http:[0,11,12,21,41,60,64,73,75,76,77],huge:6,hundr:[5,74],hyper_opt:[7,37,38,40,41,42,67],hyper_opt_method:[3,12],hyper_opt_naswot:[7,37,67],hyper_opt_oat:[7,37,67],hyper_opt_optuna:[7,37,67],hyperopt:[3,38,39,40,41,42,69],hyperoptim:[2,69],hyperoptnaswot:[40,43],hyperoptoat:[40,41,43],hyperoptoptuna:[40,42,43],hyperparam:12,hyperparamet:[0,1,2,7,12,37,38,39,40,41,42,44,45,46,47,49,51,52,56,67,68,72,73,74,76],hyperparameter_acsd:[7,37,67],hyperparameter_naswot:[7,37,67],hyperparameter_oat:[7,37,67],hyperparameter_optuna:[7,37,45,67],hyperparameteracsd:[43,44],hyperparameternaswot:[43,45],hyperparameteroat:[43,46],hyperparameteroptuna:[43,45,47],hyperparemet:12,i0:59,i1:59,i:[1,3,5,6,12,16,18,19,25,32,38,39,40,41,42,62,64,69,72,78],i_0:59,i_1:59,ibrav:61,icml2019:11,idea:6,ideal:[2,13,61,64],identif:74,identifi:69,idx:46,ifnam:60,ignor:[3,12,18,61,64,68,75],ik:62,imag:[60,64],imaginari:60,immens:0,impact:[6,63],imped:12,implement:[0,3,5,6,10,12,13,22,32,36,48,49,50,61,62,63,64,74,78],implemented_properti:36,impli:[11,13,60,64],improv:[0,1,12,23,24,72],in_unit:[30,31,32,34,58,61,62,63,64],includ:[0,4,11,12,19,28,32,40,41,54,60,63,69,70,74],incopor:70,incorpor:64,increas:[3,12],increment:[6,22,72,76],incremental_fit:22,indent:12,index:[46,76],indic:[22,26,48,49,55],indisput:12,individu:[3,6,70,72,74,78],industri:6,inf:12,infer:[0,5,12,53,54,55,60,63,71,72,74],inference_data_grid:[5,12],infinit:48,infint:48,info:[12,18,72],inform:[2,3,4,12,13,15,50,62,64,65,70,71,72],infrastructur:[0,42],inher:4,inherit:10,init_hidden:50,init_weight:50,initi:[3,13,15,50,70,74],initial_charg:36,initial_magmom:36,initial_setup:[3,6],initialis:50,initil:12,initrang:50,inject:50,input:[12,19,20,22,23,25,26,27,28,50,61,62,63,64,70,72,78],input_data_scal:[19,25,26],input_dimens:[20,25,26,72],input_directori:[20,23],input_fil:[20,23],input_npy_directori:[20,23,28],input_npy_fil:28,input_requires_grad:[25,26],input_rescaling_typ:[12,69,72],input_shm_nam:27,input_unit:[20,28],inputpp:70,insid:[75,76],instal:[0,2,5,74],instanc:[2,3,4,11,12,13,15,16,18,32],instanti:[12,50,54,56,72],instead:[2,3,5,25,26,41,49,60,64,68,70],institut:74,instruct:[0,2,5,74,75,77],integ:[5,12,18,47,69],integr:[53,59,61,62,63,71],integral_valu:59,integrate_values_on_spac:59,integration_method:[61,62,63],integration_valu:59,intel:75,intend:4,interact:4,interest:[4,5,65,69,71,72],interfac:[0,2,3,7,11,12,13,32,36,43,49,50,53,61,62,63,64,67,69,70,71],interg:[61,63],intern:[13,18,32,53,54,61,64],internal_iteration_numb:[13,61,64],interpret:6,interv:[3,6,12],introduc:[12,74],introduct:68,introductori:70,intuit:[2,6],invalid:[61,62,63,64],invalidate_target:[61,62,63,64],inverse_transform:22,investig:[5,19,20,38,39,42,43,44,45,46,47,69],involv:[2,5,6,72],io:[16,41,71],ion:12,ionic:[12,74],iop:73,ish:77,issu:[12,73],ist:64,iter:[12,13,61,64],its:[4,12,19,69,72,74],itself:[3,5,6,12,16,59,64,70,71,72,73,76],j:[60,73,74,77],jacobian:[12,40,52],jame:0,jiang:74,jmax:12,job:[3,12,42],join:[2,70,71,72],jointli:74,jon:[0,74],josh:[0,12],journal:73,json:[10,12,28,36,54,56,64,69,70],json_dict:[10,12,28],json_serializ:[7,8,12,28,43,67],jsonserializ:[10,12,28,43],judg:[6,48,49],jul:73,jun:73,june:60,jupyt:4,just:[0,2,3,4,5,12,26,54,56,71,72,78],justifi:59,k:[5,53,59,62,63,64,70,74],k_:59,keep:[0,12,25,26],kei:60,kept:[12,60],keyword:[6,12,18,71],kind:[11,13,20,23,60],kindli:[0,73],kinet:12,kmax:[5,12,64],known:[6,36],kohn:[73,74],kokko:[5,11,75],kokkos_arch_gpuarch:75,kokkos_arch_hostarch:75,kokkos_arch_hsw:75,kokkos_arch_volta70:75,kokkos_enable_cuda:75,kotik:0,kpoint:[5,64],ks:[61,62,63],kulkarni:0,kwarg:[24,25,26,27,32,36,41,48,49,50,61,63],kyle:[0,73],l2:12,l:[12,73,74,75],label:12,laboratori:74,lammp:[2,5,11,12,32,33,78],lammps_compute_fil:12,lammps_util:[7,29,67],langevin:12,larg:[2,4,5,6,32,64,72,73,74,76],larger:[5,12,13,61,64,73],last:[12,25,26,36,42,61,69,72],last_trial:42,lastli:70,latenc:6,later:[3,6,22,40,63,69],latest:41,latter:[3,13,64,70],lattic:60,launch:[3,6,12],layer:[3,12,21,39,43,44,45,46,47,69,72],layer_activ:[12,69,72],layer_activation_00:69,layer_activation_xxx:12,layer_s:[12,69,72],lazi:[12,22,23,25,26,72],lazili:[12,19],lazy_load_dataset:[7,17,67],lazy_load_dataset_singl:[7,17,67],lazyloaddataset:[25,26],lazyloaddatasetsingl:26,lbla:77,ldo:[2,5,6,7,12,18,53,55,57,58,59,61,62,64,67,70,71,72,74,78],ldos_calcul:[5,63,71],ldos_data:63,ldos_gridoffset_ev:[6,12,70,72],ldos_grids:[6,12,70,72],ldos_gridspacing_ev:[6,12,70,72],ldos_object:[61,62],ldosfil:70,lead:[2,5,12,64,74],leaf:19,leakyrelu:[12,69],learn:[6,7,12,22,64,69,72,73,74],learner:11,learning_r:[12,69,72],learning_rate_decai:[12,69],learning_rate_pati:[12,69],learning_rate_schedul:12,least:64,leastearly_stopping_threshold:12,leav:26,left:[4,27],legaci:[12,36,64],length:[5,50,73,74],lenz:[0,73,74],less:[12,18,64],let:[12,70,72],level:[11,12,21,25,26,41,53,59,62,63,72,73,74],lf:76,lfftw3:77,liabil:[11,60],liabl:[11,60],lib:[75,77],liblammp:75,librari:[3,4,5,6,22,49,69,71,72,75,77,78],licens:[11,60],lie:32,like:[3,5,6,11,26,72,77],likewis:[2,5,6],limit:[3,5,6,11,12,27,49,60,74],line:[4,33,60,72,73],linger:11,link:[11,41,69,73,75],linux:[76,77,78],list:[0,2,4,5,12,13,18,19,20,27,28,32,33,36,38,39,40,41,42,43,44,45,46,47,51,55,60,61,64,72],littl:61,llapack:77,lmkl_core:77,lmkl_intel_lp64:77,lmkl_sequenti:77,lmp:33,load:[12,19,20,22,23,25,26,27,36,39,41,42,50,53,54,56,62,69,71,72,75,77],load_from_fil:[12,22,41,42,50,69],load_from_json:12,load_from_pickl:12,load_model:[36,71],load_run:[3,6,54,56,71,72],load_runn:[54,56],load_snapshot_to_shm:27,load_with_gpu:54,load_with_mpi:54,loaded_hyperopt:41,loaded_network:[50,54,56],loaded_param:[41,42,54,56],loaded_paramet:12,loaded_train:42,local:[0,3,11,12,32,61,63,74,75],local_density_of_st:[62,63],local_offset:13,local_psp_nam:12,local_psp_path:12,local_reach:13,locat:[0,12,63],log:[0,15,59],logdir:6,logging_period:15,longer:[0,2,12,19],look:54,loos:64,loss:[6,12,41,48,50,55,69],loss_function_typ:12,loss_val:50,lot:[65,72,78],low:[12,39,43,44,45,46,47,72],lower:[16,39,43,44,45,47,69],lowest:[12,70],lstm:[12,50],m:74,mach:74,machin:[72,73,74,75,76,77],maco:[76,78],made:[0,5,71],mae:[55,72],magmom:36,magnitud:73,mai:[2,3,12,16,18,59,62,63,69,72,75,76,77],main:77,mainli:4,maintain:[0,6],mainten:[0,74],major:0,make:[0,3,4,5,6,12,52,63,70,72,74,75,76,77],mala:[1,2,3,4,6,8,9,11,12,13,15,16,18,19,20,21,23,25,26,27,28,30,31,32,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,52,53,54,55,56,58,61,62,63,64,66,67,69,70,72,75,77,78],mala_data_repo:[21,76],mala_foundational_pap:73,mala_hyperparamet:73,mala_paramet:[5,71],mala_shuffled_snapshot:23,mala_sizetransf:73,mala_temperaturetransf:73,mala_vi:6,malada_compat:16,manag:[12,24,72],mandatori:40,mani:[0,2,3,12,70,71],manual:[0,5,12,69,77],manual_se:12,map:63,mape:55,mark:42,mask:50,mass:60,massiv:[3,73],master:[0,11,64],match:[2,13,60,61,62,63,64],mater:74,materi:[5,71,73,74],mathemat:[3,38,59],mathrm:[59,61],matplotlib:5,matrix:61,matter:[5,19,73,74],max:[12,22,72],max_len:50,max_number_epoch:[12,72],maxim:12,maximum:[2,3,5,12,50,64],mc:[12,35,36],md:[12,15,16,35,36,64,74],mean:[6,12,13,22,32,48,49,52,58,61,62,63,69,70,72],mean_std:12,meaning:[12,64],measur:72,mechan:[18,49,74],medium:12,melt:74,member:[16,64],memori:[6,11,12,18,25,26,27,33,54,56,61,62,63,72],mention:[2,5,6],merchant:[11,60],merg:[0,11,60],merit:71,mess:42,messag:[1,11],meta:[13,60,65],metadata:[4,13,18,26,30,31,34,60,61,62,63,65],metadata_input_path:18,metadata_input_typ:18,method:[0,2,3,5,6,10,12,48,49,50,59,60,61,62,63,64,70,73,74,76],metric:[3,12,16,48,74],mev:6,mic:64,might:[12,26,36,42,50,52],miller:[0,73,74],mimic:60,min:[12,22,72],min_verbos:11,mini:[12,52,69],mini_batch_s:[12,69,72],minim:12,minimum:[11,12,41,64],minor:0,minterpi:0,minterpy_descriptor:[7,29,67],minterpydescriptor:34,minut:5,mit:[11,60],mitig:6,mix:[6,12,19,23,25,26],mix_dataset:[19,25,26],mkl:77,ml:[2,3,5,6,15,58,61,62,63,64,68,70,74],mlr:12,mode:[11,32,54,63,64],model:[0,2,3,5,6,18,36,50,53,54,56,68,69,70,73,74,78],modern:73,modif:[6,64],modifi:[0,11,42,48,49,60,70,77],modin:[0,73,74],modul:[0,9,21,50,60,61,64,78],modular:0,moham:[0,73,74],moldabekov:74,molecular:[71,74],moment:[5,12,19,39,43,44,45,46,47],monitor:6,month:73,more:[1,2,3,5,6,12,22,24,36,59,64,70,71,74],moreov:74,most:[2,6,12,54,73,74,75,76,77,78],move:[12,73],mpi4pi:32,mpi:[2,3,5,11,12,18,53,54,63,75,77],mpi_util:11,mpif90:77,mpirun:3,mse:[12,55],much:[6,26,62],mujoco:11,multi:[5,12],multi_lazy_load_data_load:[7,17,67],multi_train:12,multi_training_prun:[7,37,67],multilazyloaddataload:27,multipl:[1,2,3,6,11,12,16,19,20,27,28,32,39,43,44,45,46,47,48,53,59,63,69,70,72],multiple_gaussian:59,multipli:12,multiplicator_v:59,multitrainingprun:48,multivari:12,must:[12,20,63],mutat:33,mutual:[5,69],my:32,my_modified_fil:0,my_studi:3,myriad:73,mysql:3,n:[3,61,73,74],n_trial:[12,69],na:12,naiv:6,name:[0,3,6,12,13,16,18,19,23,27,32,33,36,38,39,41,42,43,44,45,46,47,54,56,61,63,64,69,70,72,75,77],naming_schem:[4,18,70],naming_scheme_input:19,naming_scheme_output:19,naswot:[0,3,12,43,45,48,49],naswot_prun:[7,37,67],naswot_pruner_batch_s:12,naswot_pruner_cutoff:12,naswotprun:49,nation:74,natom:61,natur:[0,12],ndarrai:[13,55,61,62,63,64],ndarri:13,necessari:[3,4,6,10,12,18,22,42,64,68,69,70,71,72,75],necessarili:[61,62,63,64],need:[2,5,10,12,13,19,20,25,28,32,36,50,54,56,59,61,62,63,64,70,72,75,76,77,78],neg:[6,12,64],neglect:12,neighbor:64,neighborhood:16,neither:63,net:[12,50,60],netwok:12,network:[3,6,7,12,19,22,36,38,39,40,41,42,44,45,46,47,48,49,51,52,53,54,55,56,63,67,69,71,72,73,74],neural:[3,12,36,50,53,55,56,72,73,74],neuron:[12,69,72],new_atom:32,new_datahandl:[41,42,54,56],new_hyperopt:[41,42],new_inst:11,new_runn:54,new_train:56,new_valu:11,newer:77,newli:[54,56,70],next:[6,42,60],nil:[0,73],nn:[3,5,6,50,52,64,69,72],nn_type:12,no_data:[41,42],no_hidden_st:12,no_snapshot:12,node:[11,12,42],nois:12,nomenclatur:69,non:[2,4,61,64],none:[12,13,15,16,18,19,20,22,23,28,30,31,32,33,34,36,38,39,40,41,42,43,44,45,46,47,52,53,54,56,61,62,63,64,72],noninfring:[11,60],nor:63,normal:[12,13,22,72],normand:[0,73],note:[0,5,6,12,26,33,38,39,41,42,43,44,45,46,47,49,59,71,75],notebook:[4,41],noteworthi:69,noth:[5,30,31,34],notic:[11,60],now:[4,27,63,65,69,70,71,72,77],np:[3,13,19,59,60,63],npj:[73,74],npy:[2,4,6,18,70,72],nsy:12,num_choic:46,num_head:12,num_hidden_lay:12,num_work:[6,12],number:[0,3,5,6,11,12,13,16,18,19,23,33,36,41,46,55,60,61,62,63,64,66,69,70,72,73,74,77],number_bad_trials_befor:12,number_bad_trials_before_stop:12,number_of_bin:[5,12,64],number_of_electron:[55,61,62,63,72],number_of_run:41,number_of_shuffled_snapshot:[6,23],number_training_per_tri:[3,12],numer:[12,13,16,25,32,39,43,44,45,47,60,61,62,63,64],numpag:73,numpi:[0,2,4,13,18,19,20,22,23,26,27,28,30,31,32,33,34,46,51,53,55,58,59,60,61,62,63,64,65,70],numpy_arrai:19,nvcc_wrapper:75,nvidia:[6,75],o:[12,19],oa:[39,41,43,44,45,46,47,51],oapackag:[41,76],oat:[0,3,12,43,46,51,52],object:[0,3,4,5,6,10,12,13,15,16,18,19,20,22,23,26,27,28,30,31,32,33,34,36,38,39,40,41,42,48,49,50,51,52,53,54,55,56,58,60,61,62,63,64,69,70,71,72],objective_bas:[7,37,52,67],objective_naswot:[7,37,67],objectivebas:[51,52],objectivenaswot:52,observ:[55,71,72,74],observables_to_test:[55,72],obtain:[5,11,19,60,76],occur:[42,59,72,76],oct:73,ofdft_frict:12,ofdft_initi:[7,14,67],ofdft_kedf:12,ofdft_number_of_timestep:12,ofdft_temperatur:12,ofdft_timestep:12,ofdftiniti:15,off:[0,12],offer:[4,6,12,65,74],offici:[4,12,68,71,75,76],offload:[5,6],often:[6,12],ol:[0,73,74],old:[12,28],omar:0,onc:[0,1,2,3,5,6,42,60,69,70,72],one:[2,3,4,5,6,11,12,16,19,20,23,32,48,53,60,61,62,63,64,69,70,72,74,78],ones:[5,25,26,32,69],ongo:76,onli:[0,1,2,3,5,6,11,12,13,16,18,19,20,22,25,26,28,33,36,41,42,50,53,54,55,59,60,61,62,63,64,65,69,70],onto:0,onward:6,open:[0,4,13,60,76],openmpi:77,openpmd:[0,1,12,13,18,20,23,28,32,61,62,63,64],openpmd_configur:12,openpmd_granular:12,oper:[5,6,11,12,19,20,23,64,70,72,74,76],opt:76,optim:[0,1,2,5,6,12,30,32,38,39,40,41,42,49,51,52,56,64,68,72,73,74,76],optimal_sigma:30,optimizer_dict:56,option1:75,option2:75,option:[3,4,6,9,11,12,13,18,22,26,28,30,31,32,34,38,40,54,56,60,64,69,70,72,73,74,75,78],opttyp:[39,41,43,44,45,46,47],optuna:[3,12,39,41,42,43,44,45,46,47,48,49,51,52,69],optuna_singlenode_setup:[3,12],orbit:74,order:[0,3,6,11,12,13,19,25,26,41,69,70,71,73,76],org:[38,60,64,73],orient:0,origin:[3,11,20,28,33,60,73],orthogon:[3,12,41,46,51,76],os:[2,70,71,72],oscil:16,ot:[25,26],other:[3,6,10,11,16,32,35,60,61,62,64,69,71,74],otherwis:[11,39,56,60],otherwsi:22,our:[4,73],ourselv:22,out:[0,2,4,6,11,19,40,41,53,60,62,64,70,71,72,75,76],out_unit:[30,31,32,34,61,62,63,64],outfil:[32,70],outlin:[6,59],output:[1,2,6,11,12,18,19,20,22,23,25,26,27,28,30,31,32,34,50,55,57,60,61,62,63,64,70,72,76,78],output_data_scal:[19,25,26],output_dimens:[20,25,26,72],output_directori:[20,23],output_fil:[20,23],output_format:[55,72],output_npy_directori:28,output_npy_fil:[20,23,28],output_rescaling_typ:[12,72],output_shm_nam:27,output_unit:[20,28],outsid:[32,63],over:[1,2,64],overal:0,overfit:72,overflow:59,overhead:[3,12,73],overview:[1,75],overwrit:[18,23,26],overwritten:[54,60],own:[4,12,50,72],p:[60,73,74,75],packag:[74,75,78],page:73,pairs:60,paper:[41,48,49,73],parallel:[0,1,4,7,8,12,22,32,63,67,68,74,75],parallel_warn:11,param:[30,31,32,34,36,38,39,40,41,42,50,51,53,54,55,56,58,60,61,62,63,64,69],paramet:[2,3,4,5,6,7,8,10,11,13,15,16,18,19,20,22,23,25,26,27,28,30,31,32,33,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,58,59,60,61,62,63,64,65,67,69,70,71,74],parametersbas:12,parametersdata:12,parametersdatagener:12,parametersdebug:12,parametersdescriptor:[12,38],parametershyperparameteroptim:12,parametersnetwork:12,parametersrun:[12,52],parameterstarget:[12,64],parametr:19,params_format:[54,56],paraview:4,parent:54,pars:[2,12,18,29,30,31,34,38,51,58,61,62,63,65],parse_tri:51,parse_trial_oat:51,parse_trial_optuna:51,parser:[60,64],part:[5,13,60,61,64,72,78],particl:[12,64],particular:[11,48,49,60],partit:55,parvez:[0,73],pass:[0,12,50,53,63],path:[2,6,12,13,16,18,19,21,36,38,41,42,50,53,54,56,61,62,63,64,70,71,72,75,76,77],path_name_schem:63,path_schem:63,path_to_fil:[50,53],path_to_visu:6,patienc:12,paulbourk:60,pavanello:74,pbc:[32,36],peform:12,penalti:12,peopl:0,pep8:0,per:[12,32,36,69,72],percent:12,perform:[1,3,5,12,18,19,22,24,26,36,38,39,40,41,42,50,53,59,62,63,64,68,70,71,72,73,74,75,78],perform_studi:[2,38,39,40,41,42,69],permiss:[11,60],permit:[11,60],permut:26,person:[11,60,70],phase:73,phenomena:73,phy:[73,74],phyiscal:6,physic:[2,3,6,12,13,57,64,73],physical_data:[7,8,32,64,67],physicaldata:[13,32,64],physrevb:73,pickl:[12,22,32],pip:76,pipelin:[19,20,23],pkg_kokko:75,pkg_ml:75,pkl:[39,41,42,54,56],place:[22,72],plan:75,plane:5,plateau:[12,69],plea:64,pleas:[0,2,3,4,5,6,12,38,39,41,42,43,44,45,46,47,63,69,71,72,73,74,75,76],plot:[2,5,64],plu:[3,12],plugin:4,pmd:4,point:[2,3,5,6,12,21,25,26,33,54,62,64,70,72,74],popoola:[0,73,74],popular:73,portion:[11,18,60],pose:74,posit:[7,32,36,50,53,60,61,70,71],positionalencod:50,possibl:[6,12,38,39,43,44,45,46,47,50,62,69],post:[4,28,64,74,78],postgresql:3,postprocess:[7,58,61,62,63,64],potenti:[0,32,69,74],power:[4,6,71],pp:70,pr:0,practic:6,pre:[0,27],precalcul:78,preced:70,precict:[53,55],precis:[6,12,18,33],predict:[6,7,36,50,53,55,63,64,68,72,73,74],predict_for_atom:[5,53,71],predict_from_qeout:53,predict_target:55,predicted_arrai:50,predicted_ldo:53,predicted_output:55,predictor:[5,7,37,54,56,67,71],prefer:[36,70],prefetch:[6,12,26],prepar:[6,13,19,41,42],prepare_data:[19,54,56,69,72],prepare_for_test:19,preprocess:[2,7,12,32,64,70],present:[13,38,39,40,41,42,54,61,64],press:[12,73],previou:[50,71],primari:69,principl:[2,5,39,43,44,45,46,47,72,74],print:[1,3,6,11,12,41],printout:[1,3,11],prior:[0,2,5,6,12],priorli:16,problem:[6,77],problemat:12,proceed:12,process:[0,2,3,4,6,11,12,18,19,22,25,26,28,32,33,38,51,64,70,71,72,73,74,75,77,78],product:[1,4,6,53,72,75],profil:12,profiler_rang:12,progress:[6,63],project:[0,4,21,75,76],proof:74,proper:[61,62,63,73],properli:[0,11,12],properti:[6,10,12,13,16,20,25,28,30,31,32,34,36,46,61,62,63,64,69,71,74],provid:[2,3,5,6,11,12,13,16,18,21,23,38,40,49,59,60,61,62,63,64,65,70,71,72,75,76],prudent:[3,72],prune:[48,49],pruner:[12,48,49],pseudopotenti:[12,61,63,64,71],pseudopotential_path:[12,71],psu:64,publish:[0,11,60,73],pure:[6,45,62],purpos:[2,11,41,42,60],push:0,put:[5,12,19,42,50],pw:[61,70],py:[0,2,3,6,11,71,72,75],pypi:0,pyproject:0,pytest:76,python3:[3,75],python:[2,3,4,5,19,20,32,33,61,64,71,78],pythonpath:77,pytorch:[12,19,50],q:77,qe:[12,32,53,61,62,63,64,77,78],qe_input_data:[61,63,64],qe_out_fil:32,qe_pseudopotenti:[61,63,64],qef:77,qualiti:0,quantif:0,quantit:12,quantiti:[12,16,18,22,55,57,61,62,63,64],quantum:[5,18,32,61,62,63,64,70,71,73,74,78],quantumespresso:64,question:6,queue:42,quick:32,r:[41,60,63,76],race:3,radial:[5,12,64],radial_distribution_funct:64,radial_distribution_function_from_atom:[5,64],radii:[2,5,12,64],radiu:[2,12,64,70],rais:61,rajamanickam:[0,73,74],ram:[6,25,41,42,50,63],random:[6,50],randomli:3,rang:[2,12,22,41,50,72,73,74],rank:[3,11,12,32,53,62,63],rapid:74,rate:[6,12,50,69],rather:[3,19,61,62,63],raw:[2,18,19,32,70],raw_numpy_to_converted_scaled_tensor:19,rawradialdistribut:64,rdb:[12,42],rdb_storag:[3,12,42],rdb_storage_heartbeat:12,rdf:[5,12,16,36,64],rdf_paramet:12,re:[0,2,19],read:[4,10,12,13,16,22,25,26,28,53,59,60,61,62,63,64,65,71],read_additional_calculation_data:[62,64],read_additional_read_additional_calculation_data:61,read_cub:60,read_dimensions_from_numpy_fil:13,read_dimensions_from_openpmd_fil:13,read_dtyp:13,read_from_arrai:[61,62,63,71],read_from_cub:[61,63],read_from_numpy_fil:13,read_from_openpmd_fil:13,read_from_qe_dos_txt:62,read_from_qe_out:62,read_from_xsf:[61,63],read_imcub:60,read_xsf:65,readi:[70,72],readlin:60,readthedoc:41,real:[22,60,64,69,72,74,78],realist:78,realli:[30,31,34,36],realspac:[5,16],reason:[6,12,19,62,65,72],rebas:0,recap:6,recent:[73,74,75,76,77],recogn:12,recommend:[6,12,16,61,62,63,64,75,78],reconstruct:[41,42,54,56],record:12,recv:32,redistribut:23,reduc:[12,26,63,70],reducelronplateau:12,reduct:12,refer:[2,3,12,61,68,69,70,72,74,75],reference_data:36,reflect:[5,61,63],reformat:0,regain:26,regard:73,regular:[2,3,5,12,52,70],regularli:0,reimplement:10,rel:[26,50,62],relat:[3,12,75],releas:77,relev:[2,4,6,12],reli:[5,73],relu:[12,69,72],remark:[2,5],remind:[2,5],remov:32,renam:77,reorder:[12,62],reparametrize_scal:19,replac:[4,13,18,28,60,63,74],repo:[0,76],report:[3,12,48,49],repositori:[0,12,68,72,73,74,76,77],repres:[2,12,28,44,45,46,47,51,52,70,72],represent:[45,70,74],reproduc:[0,6,62,63,64],request:[12,41,73],requeue_zombie_tri:42,requir:[0,3,5,6,12,13,26,40,41,60,70,72,75,76,78],research:[73,74],reset:[19,20],reshap:[13,61],resiz:19,resize_snapshots_for_debug:19,resp:[5,12],respect:[3,10,12,20,70,72,73],respres:[46,51],restart:3,restrict:[11,12,60,64],restrict_data:64,restrict_target:12,resubmit:42,result:[3,6,12,18,19,33,51,55,64,70,71,72,74],result_typ:33,resultsfor:74,resum:[3,6,41,42],resume_checkpoint:[41,42],resumpt:[6,41,42],retain:[32,60],return_energy_contribut:63,return_outputs_directli:25,return_plot:[2,38],return_str:64,return_valu:[46,47],retval:60,reusabl:0,rev:[73,74],rewrit:26,rfname:60,right:[11,19,50,60],rmax:[12,64],robust:3,romero:[0,12],room:74,root:[0,22],rossendorf:74,roughli:73,rout:32,routin:[2,4,6,12,72],row:[12,22,46,51,72],rst:76,run:[0,3,5,11,12,25,32,36,41,42,53,54,56,63,69,72,76,77],run_exist:[3,6,54,56],run_nam:[36,54,56],runner:[7,37,53,55,56,67],runner_dict:54,runtim:4,ry:[2,58,62,63,70],s0:59,s1:59,s41524:73,s:[0,12,39,41,60,62,64,72,73,74,77],safe:1,sai:77,same:[3,6,12,18,19,20,23,32,38,42,50,59,60,63,64,69,77],samefileerror:75,sampl:[12,16,38,39,40,41,42,70,72],sampler:[12,41],sandia:74,save:[3,4,5,6,10,12,13,16,18,19,20,22,23,28,36,41,42,50,54,56,61,62,63,64,69,70,71,72],save_as_json:12,save_as_pickl:12,save_calcul:36,save_format:[12,22],save_nam:[4,6,23],save_network:50,save_path:[36,54],save_run:[54,72],save_runn:54,scalabl:74,scalar:33,scale:[3,4,5,6,12,19,22,25,26,41,42,50,61,63,69,72,73,74,76],scaled_posit:61,scaler:22,scarc:18,scf:61,schedul:[12,42],scheme:[18,19,63],schmerler:[0,73,74],sci:74,scienc:73,scientif:[0,4,74],scikit:22,score:[48,49],script:[3,5,11,12,69,77],se:36,search:[1,2,69],search_paramet:[48,49,52],second:12,secondli:[2,72],section:[6,68,69,70,71,72],see:[0,2,5,12,18,20,28,38,41,60,64,70,71,72,75,77],seed:[6,12],seem:[5,26],select:[2,6,12,13,55,70,72,77],self:[62,63],sell:[11,60],sendv:32,sens:[12,36,52,54,62,63,72],sep:[11,73],separ:[11,18,28,36,54,56,70,72,78],sequenc:50,seri:[4,13],serial:[10,11],serializ:10,serv:[50,53,74],server:42,servernam:3,set:[0,2,3,4,5,6,11,12,13,16,18,19,23,24,25,26,27,32,38,39,40,41,42,51,53,54,55,61,62,63,64,69,70,71,74,75],set_calcul:71,set_cmdlinevar:33,set_current_verbos:11,set_horovod_statu:11,set_lammps_inst:11,set_mpi_statu:11,set_optimal_paramet:[2,38,39,40,41,42,69],set_paramet:39,setup:[0,3,6,35,76],sever:[3,5,59,69,72],sgd:12,sh:77,shall:[11,60],sham:[73,74],shao:74,shape:[33,61,64],share:[26,27],shift:32,ship:75,shorter:6,should:[0,2,3,5,6,11,12,13,19,21,22,30,31,32,34,36,41,42,47,48,49,50,53,54,58,59,61,62,63,64,69,70,72,75,77],should_prun:[48,49],show:[0,12,74],show_order_of_import:41,showcas:[2,74],shown:[2,3,5,6,70,72],shuffl:[0,4,6,12,20,23,24,25,26],shuffle_snapshot:[4,6,23],shuffling_se:[6,12],shut:11,shutil:75,si:[13,32,61,62,63,64],si_dimens:[13,32,61,62,63,64],si_unit_convers:[13,32,61,62,63,64],sigma:[12,30,59],sigmoid:[12,69],sign:0,signal:72,signific:[12,74],significantli:[63,64],silver:73,similar:[2,3,16,74],simp:[59,61,62,63],simpl:[70,71,72],simplest:6,simpli:[5,6,12,16,19,36,51,61],simpson:[59,61,62,63],simul:[5,12,36,60,61,63,70,71,72,73,74,78],sinc:[2,3,5,6,12,18,30,31,32,34,36,42,71,72,76],singl:[3,5,18,24,26,33,55,68],site:13,siva:0,sivasankaran:[73,74],six:36,size:[0,3,5,11,12,13,26,39,43,44,45,46,47,50,52,69,72,74],skip:33,skiparraywrit:13,slice:[5,19],slightli:42,slowest:12,small:[2,6,64,78],smaller:[12,25,69],smallest:[12,16],smear:62,smearing_factor:62,smith:64,smoothli:12,snap:[12,75],snapshot4:18,snapshot:[6,7,12,15,16,17,18,19,20,23,25,26,27,32,38,55,63,67,70,72],snapshot_correlation_cutoff:16,snapshot_directories_list:12,snapshot_funct:28,snapshot_numb:[19,55,63],snapshot_typ:[4,20,23,28],sneha:0,so:[2,3,4,6,11,12,22,50,54,60,61,62,70,72,74,75,76,77,78],societi:73,softwar:[0,5,11,60,70,71,73,74,78],sole:75,solv:59,somashekhar:0,some:[2,6,12,25,26,50,52,54,64,72],someth:[52,77],sometim:76,somewhat:12,soon:7,sort:[22,25,26,32,41],sourc:[0,9,10,11,12,13,15,16,18,19,20,22,23,24,25,26,27,28,30,31,32,33,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,58,59,60,61,62,63,64,65,71],space:[2,6,59,62,64,69,70,72,74,78],special:[2,24],specif:[3,4,6,12,19,39,50,59,64,71,76],specifi:[0,2,3,4,5,6,12,13,22,32,52,62,64,69,70,71,72],speed:[6,12,74],speedup:6,sphere:70,sphinxopt:76,split:[5,12],springer:41,sql:[3,42],sqlite:[3,12],sqlite_timeout:12,sqrt:59,squar:[6,12],src:75,srcname:60,ssf:[12,64],ssf_paramet:12,stabl:12,standard:[3,4,5,12,22,69,72],start:[2,3,5,12,22,70],start_incremental_fit:22,starts_at:18,state:[12,50,62,63,71,74],statement:[5,11],static_structur:5,static_structure_factor_from_atom:[5,64],statu:11,stem:[62,63],step:[2,5,12,15,16,68,69,78],stephen:[0,73,74],steve:[0,73],still:[6,11,13,24,27,41,42,73,74],stochast:12,stop:[12,19,69,76],storag:[4,12,42],store:[1,3,12,25,26,36,61,64,70,72],str:[27,36,54,55,56,61,63],straightforward:[0,2,74],strategi:[3,69],strength:41,stress:36,stretch:5,string:[11,12,13,16,18,19,20,22,23,28,30,31,32,33,34,36,38,39,41,42,43,44,45,46,47,50,52,53,54,55,56,58,59,60,61,62,63,64,65],structur:[5,7,12,13,64,70,71,72,73,74,78],studi:[3,12,38,39,40,41,42,48,49,69,73],study_nam:[3,12,42],style:[0,51,64],sub:72,subclass:[43,50],subfold:12,subject:[11,60,76],sublicens:[11,60],submit:0,subobject:72,subroutin:63,subsequ:[12,53,74],subset:[39,40,42],substanti:[11,60],success:[75,77],successfulli:[75,76],suffic:32,suffici:0,suggest:[0,12,16,64],suit:[0,77],suitabl:[5,12,73,74,75,76],sum_i:62,sum_k:62,summari:64,summat:[61,63,64],supervis:0,supervisor:74,support:[0,3,4,5,6,12,20,28,36,39,41,43,44,45,46,47,52,55,58,59,61,62,63,64,75],suppos:[0,33,49,59,63],suppress:59,suppress_overflow:59,sure:[0,3,4,6,32,63,70,72,74,75,76,77],surrog:[12,48,49,74],switchflag:12,symbol:18,symmetri:[61,63],syntax:[2,3,6,72,76],system:[0,2,3,5,6,12,42,61,62,63,64,71,72,74,77],system_chang:36,t:[4,12,41,42,59,60,62,63,64,74,76],tag:[0,76],tahmasbi:0,take:[2,6,12,42,48,49,64],taken:[41,60],tamar:73,target:[2,6,7,11,12,16,18,19,20,23,25,26,27,28,30,31,34,36,38,48,49,50,53,58,61,62,63,67,70,71,72],target_calcul:[5,16,18,19,20,23,25,26,27,38,71],target_calculation_kwarg:70,target_calculator_kwarg:18,target_data:64,target_input_path:[18,38,70],target_input_typ:[18,38,70],target_save_path:[18,23,70],target_temperatur:16,target_typ:[12,70,72],target_unit:[2,18,38,70],targetbas:[58,62],task:[12,59,72,78],te:[20,28,55,72],te_mutex:61,team:[0,4,5,6,75,76],technic:[32,64],techniqu:[3,70,74],technol:74,technolog:73,tell:[3,72,75],tem:[12,64],temperatur:[5,6,12,16,36,53,59,62,63,64,72,73,74],tempor:16,ten:5,tend:64,tensor:[19,22,24,50,63],tensorboard:[0,12],tensordataset:[6,12,24],term:[50,62,63],termin:12,test:[0,4,6,12,19,20,21,25,28,48,49,53,55,69,70,76,77,78],test_al_debug_2k_nr:19,test_all_snapshot:[55,72],test_exampl:0,test_snapshot:55,tester:[6,7,19,37,53,54,56,67,72],text:4,than:[12,69],thei:[0,3,4,5,6,12,42,64,71],them:[0,6,23,32,62,70],themselv:[4,16,19],theorem:61,theori:[3,73,74],thereaft:[62,64],therefor:[4,25,26,32,61,78],therein:[12,73],thermodynam:59,thi:[0,1,2,3,4,5,6,10,11,12,13,15,16,18,19,20,22,23,24,25,26,27,28,30,31,32,33,34,36,38,39,40,41,42,46,48,49,50,51,52,53,54,55,56,58,59,60,61,62,63,64,68,69,70,71,72,73,74,75,76,77,78],thing:[69,70],third:72,thompson:[0,73,74],those:[12,72,77],though:[12,64],thousand:5,thread:11,three:[5,12,64,72,78],three_particle_correlation_function_from_atom:64,threshold:16,through:[3,11,50,61,72],throughout:55,thrown:11,thu:[0,6,12,19,76],time:[0,3,5,6,12,42,70,72,73,77],timeout:12,timestep:[12,16],timothi:0,titl:73,tmp:70,to_json:[10,12],togeth:[6,69],token:50,toml:[0,12],too:[2,32],tool:[4,14,15,16,64],topic:[70,71],torch:[6,18,19,22,24,25,26,50,63,76],tort:[11,60],total:[0,5,12,55,61,62,63,64,71,72,74,78],total_energi:[12,55,63,71,77],total_energy_contribut:61,total_energy_ful:55,total_energy_modul:77,tpcf:[12,64],tpcf_paramet:12,tpe:41,tr:[4,20,28,55,72],track:19,train:[0,1,2,3,5,7,12,19,20,23,25,28,36,40,41,42,48,49,51,52,54,56,64,68,69,71,73,74,76,78],train_network:[56,72],trainer:[3,6,7,12,37,67,72],training_report_frequ:12,trainingtyp:[12,69,72],traj:15,trajectori:[12,15,16,64],trajectory_analysis_below_average_count:12,trajectory_analysis_correlation_metric_cutoff:12,trajectory_analysis_denoising_width:12,trajectory_analysis_estimated_equilibrium:12,trajectory_analysis_temperature_tolerance_perc:12,trajectory_analyz:[7,14,67],trajectoryanalyz:16,transfer:[0,6,73,74],transform:[12,19,22,25,50,61,64,70],transformernet:50,trapezoid:[59,61,62,63],trapz:[59,61,62,63],treat:[11,76],tree:[0,75],trex:11,trial:[3,12,39,40,41,42,46,47,48,49,51,69],trial_ensemble_evalu:12,trial_list:40,trial_typ:52,tricki:24,trivial:[2,5,6],truth:72,tune:[0,3,6,12,41,69,72],turn:6,tutori:[4,72],tweak:[68,71],twice:[5,64],two:[2,12,13,16,60,69,72,73],twojmax:12,txt:[0,62,76],type:[10,11,12,13,16,18,19,22,24,28,30,31,32,33,34,36,38,39,41,42,43,46,47,48,49,50,53,54,55,56,58,59,60,61,62,63,64,70],typestr:22,typic:75,u:3,ubuntu:78,uncach:[16,61,62,63],uncache_properti:[16,61,62,63],uncertainti:0,unchang:[26,61],uncorrel:[12,16],under:[0,36,54,56],underlin:63,understand:74,uniform:[50,59],unit:[13,18,19,20,23,25,26,27,28,30,31,32,34,38,50,58,61,62,63,64],unless:61,unload:6,unnecessari:[19,54],unscal:22,unseen:72,untest:77,until:[12,25,26,69,70],untouch:4,up:[0,2,6,12,32,42,61,62,63,64,69,70,74],updat:0,upon:[0,3,12,19,42,45,50,70],upper:[5,69],upward:12,url:73,us:[0,1,2,3,4,7,11,12,13,15,16,18,19,20,22,23,24,25,26,27,30,31,32,33,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,52,53,54,55,56,58,59,60,61,62,63,64,68,69,70,72,73,74,75,76,77,78],usag:[0,5,6,19,54,63,68,71,72,74,75],use_compress:12,use_fast_tensor_data_set:[6,12],use_fp64:[18,33],use_gauss_ldo:70,use_gpu:[5,6,12],use_graph:[6,12],use_horovod:[12,22,25,26],use_lammp:12,use_lazy_load:[6,12,72],use_lazy_loading_prefetch:[6,12],use_memmap:63,use_mixed_precis:[6,12],use_mpi:[2,3,5,12],use_multivari:12,use_pickled_comm:32,use_pkl_checkpoint:[38,39,40,41,42,56],use_shuffling_for_sampl:12,use_y_split:[5,12],use_z_split:12,useabl:70,used_data_handl:63,user:[4,11,12,16,48,49,59,63,72,76],userwarn:11,usual:[5,6,12,16,32,50,51,61,62,64,70],util:[6,24,25,26],v1:76,v2:12,v80:12,v:[74,75],v_:61,va:[20,28,55,72],vaidyanathan:60,valid:[3,6,12,19,20,28,69,72],validation_loss:12,validation_loss_old:12,valu:[2,5,6,11,12,13,16,25,26,30,32,40,41,46,47,48,49,50,52,53,55,59,60,61,62,63,64,69,70,72],valuabl:0,vari:77,variabl:[12,16,19,54,64],varianc:25,varieti:74,variou:[12,71,72,74],vector:[2,12,25,26,32,60,64,70,72],verbos:[11,12,62,70,72],veri:[0,3,6,12,50,62],verif:72,verifi:72,verma:0,versatil:74,version:[7,12,18,24,48,49,67,70,75,76,77],via:[0,2,3,5,6,11,12,16,21,26,61,62,63,64,69,70,71,72,75,76,77,78],viabl:48,view:[2,6,33],viewdoc:64,viewer:4,virtu:6,visibl:50,visit:[3,4],visual:[4,6,12,74],visualis:[6,12],visualisation_dir:[6,12],visualisation_dir_append_d:12,visualizatuon:6,vladyslav:[0,73],vogel:[0,73,74],volta:75,volum:73,volumetr:[4,60,65,70,72],voxel:[30,61,63],w:[41,63,76],w_k:62,wa:[5,6,22,25,26,38,39,40,41,42,50,54,56,61,62,63,64,71],wai:[0,3,6,12,64],wait:[12,42],wait_tim:[3,12],want:[2,5,6,20,23,39,43,44,45,46,47,64,69,72,75,76],warmli:0,warn:[3,11,76],warranti:[11,60],wave:[12,64],wavefunct:61,we:[0,2,3,5,12,22,25,26,32,36,64,65,69,70,72,73,75,77],websit:[3,76],weight:[6,12,50,59,72],weight_decai:12,welcom:0,well:[2,3,6,12,61,68,69,76],were:[5,72],what:[0,20,23,32,36,54,56,60,72],whatev:75,when:[0,1,3,4,6,11,12,18,19,20,28,32,42,48,49,50,54,56,60,63,64,69,70,72,77,78],whenev:72,where:[4,5,6,12,26,36,41,42,54,56,72,75],wherea:70,whether:[9,11,12,25,32,48,49,60],which:[0,2,3,4,5,6,9,12,13,15,16,18,19,20,21,22,23,28,30,31,32,33,34,36,38,39,40,41,42,46,47,48,49,50,51,53,54,55,56,58,59,60,61,62,63,64,69,70,71,72,75,76,77,78],whom:[11,60],wide:74,width:[12,30],window:[76,78],wip:63,wise:[6,12,22,69,72],wish:[5,77],within:[2,11,12,13,19,24,63,72],without:[0,3,6,11,12,13,40,52,59,60,64,75],won:[41,42],wonjoon:11,work:[0,3,5,11,12,33,40,55,60,61,62,63,64,69,77,78],worker:[6,12],workflow:[2,3,4,5,6,28,35,71,72,73,74],working_directori:[32,70],world:22,worldwid:74,would:[2,13,61],wrap:0,write:[4,13,32,60,61,64],write_additional_calculation_data:64,write_cub:60,write_imcub:60,write_tem_input_fil:64,write_to_cub:[5,61],write_to_numpy_fil:[13,64],write_to_openpmd_fil:[13,61,64],write_to_openpmd_iter:13,written:[38,39,40,41,42,61,64],wuantiti:[61,62,63,64],x86_64:77,x:[5,12,19,32,50,59,64,70,74],xarg:0,xc:61,xcrysden:63,xsf:[61,63,65],xsf_parser:[7,57,67],xvec:60,xyz:[12,32],y:[5,12,19,32,64],yaml:0,ye:75,year:73,yet:[4,6,13,30,31,34,64],yield:[2,6],you:[0,2,3,4,5,6,12,20,23,39,43,44,45,46,47,50,68,70,71,72,73,74,75,76,77,78],your:[0,2,4,5,6,12,70,72,73,74,75,76,77],yourself:68,yovel:[73,74],ysplit:5,yt:4,yvec:60,z:[5,12,19,32,64,73,74],zentrum:74,zero:[5,12,50,69],zero_out_neg:12,zip:[36,54,56,72],zip_run:[54,56],zipextfil:[12,22,50],zombi:42,zone:59,zvec:60},titles:["Contributions","Advanced options","Improved data conversion","Improved hyperparameter optimization","Storing data with OpenPMD","Using MALA in production","Improved training performance","mala","common","check_modules","json_serializable","parallelizer","parameters","physical_data","datageneration","ofdft_initializer","trajectory_analyzer","datahandling","data_converter","data_handler","data_handler_base","data_repo","data_scaler","data_shuffler","fast_tensor_dataset","lazy_load_dataset","lazy_load_dataset_single","multi_lazy_load_data_loader","snapshot","descriptors","atomic_density","bispectrum","descriptor","lammps_utils","minterpy_descriptors","interfaces","ase_calculator","network","acsd_analyzer","hyper_opt","hyper_opt_naswot","hyper_opt_oat","hyper_opt_optuna","hyperparameter","hyperparameter_acsd","hyperparameter_naswot","hyperparameter_oat","hyperparameter_optuna","multi_training_pruner","naswot_pruner","network","objective_base","objective_naswot","predictor","runner","tester","trainer","targets","atomic_force","calculation_helpers","cube_parser","density","dos","ldos","target","xsf_parser","version","API reference","Getting started with MALA","Basic hyperparameter optimization","Data generation and conversion","Using ML-DFT models for predictions","Training an ML-DFT model","Citing MALA","Welcome to MALA!","Installing LAMMPS","Installing MALA","Installing Quantum ESPRESSO (total energy module)","Installation"],titleterms:{"do":62,"public":74,ASE:71,acsd_analyz:38,ad:[0,72,76],advanc:[1,3,6],algorithm:3,an:72,api:67,ase_calcul:36,atomic_dens:30,atomic_forc:58,basic:69,behind:74,bispectrum:31,branch:0,build:[72,75,76,77],calcul:71,calculation_help:59,check_modul:9,checkpoint:[3,6],cite:73,code:0,common:8,content:74,contribut:0,contributor:0,convers:[2,70],cpu:5,creat:0,cube_pars:60,data:[2,4,70,72,76],data_convert:18,data_handl:19,data_handler_bas:20,data_repo:21,data_scal:22,data_shuffl:23,datagener:14,datahandl:17,densiti:61,depend:0,descriptor:[2,29,32],develop:0,dft:[71,72],document:76,doe:74,download:76,energi:77,espresso:77,exampl:76,extens:[75,77],fast_tensor_dataset:24,format:0,gener:70,get:68,gpu:[5,6],how:74,hyper_opt:39,hyper_opt_naswot:40,hyper_opt_oat:41,hyper_opt_optuna:42,hyperparamet:[3,43,69],hyperparameter_acsd:44,hyperparameter_naswot:45,hyperparameter_oat:46,hyperparameter_optuna:47,improv:[2,3,6],instal:[75,76,77,78],interfac:35,issu:0,json_serializ:10,lammp:75,lammps_util:33,lazi:6,lazy_load_dataset:25,lazy_load_dataset_singl:26,ldo:63,librari:76,licens:0,list:69,load:6,local:76,mala:[0,5,7,68,71,73,74,76],metric:6,minterpy_descriptor:34,ml:[71,72],model:[71,72],modul:77,multi_lazy_load_data_load:27,multi_training_prun:48,naswot_prun:49,network:[37,50],objective_bas:51,objective_naswot:52,observ:5,ofdft_initi:15,openpmd:4,optim:[3,69],option:[1,76],parallel:[2,3,5,11],paramet:[12,72],perform:6,physical_data:13,predict:[5,71],predictor:53,prerequisit:[75,76,77],product:5,pull:0,python:[75,76,77],quantum:77,recommend:76,refer:67,releas:0,request:0,run:6,runner:54,search:3,set:72,snapshot:28,start:[68,74],store:4,strategi:0,target:[57,64],tensorboard:6,test:72,tester:55,total:77,train:[6,72],trainer:56,trajectory_analyz:16,tune:2,us:[5,6,71],version:[0,66],visual:5,welcom:74,what:74,where:74,who:74,work:74,xsf_parser:65}})
\ No newline at end of file
+Search.setIndex({docnames:["CONTRIBUTE","advanced_usage","advanced_usage/descriptors","advanced_usage/hyperparameters","advanced_usage/openpmd","advanced_usage/predictions","advanced_usage/trainingmodel","api/mala","api/mala.common","api/mala.common.check_modules","api/mala.common.json_serializable","api/mala.common.parallelizer","api/mala.common.parameters","api/mala.common.physical_data","api/mala.datageneration","api/mala.datageneration.ofdft_initializer","api/mala.datageneration.trajectory_analyzer","api/mala.datahandling","api/mala.datahandling.data_converter","api/mala.datahandling.data_handler","api/mala.datahandling.data_handler_base","api/mala.datahandling.data_repo","api/mala.datahandling.data_scaler","api/mala.datahandling.data_shuffler","api/mala.datahandling.fast_tensor_dataset","api/mala.datahandling.lazy_load_dataset","api/mala.datahandling.lazy_load_dataset_single","api/mala.datahandling.multi_lazy_load_data_loader","api/mala.datahandling.snapshot","api/mala.descriptors","api/mala.descriptors.atomic_density","api/mala.descriptors.bispectrum","api/mala.descriptors.descriptor","api/mala.descriptors.lammps_utils","api/mala.descriptors.minterpy_descriptors","api/mala.interfaces","api/mala.interfaces.ase_calculator","api/mala.network","api/mala.network.acsd_analyzer","api/mala.network.hyper_opt","api/mala.network.hyper_opt_naswot","api/mala.network.hyper_opt_oat","api/mala.network.hyper_opt_optuna","api/mala.network.hyperparameter","api/mala.network.hyperparameter_acsd","api/mala.network.hyperparameter_naswot","api/mala.network.hyperparameter_oat","api/mala.network.hyperparameter_optuna","api/mala.network.multi_training_pruner","api/mala.network.naswot_pruner","api/mala.network.network","api/mala.network.objective_base","api/mala.network.objective_naswot","api/mala.network.predictor","api/mala.network.runner","api/mala.network.tester","api/mala.network.trainer","api/mala.targets","api/mala.targets.atomic_force","api/mala.targets.calculation_helpers","api/mala.targets.cube_parser","api/mala.targets.density","api/mala.targets.dos","api/mala.targets.ldos","api/mala.targets.target","api/mala.targets.xsf_parser","api/mala.version","api/modules","basic_usage","basic_usage/hyperparameters","basic_usage/more_data","basic_usage/predictions","basic_usage/trainingmodel","citing","index","install/installing_lammps","install/installing_mala","install/installing_qe","installation"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":5,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,"sphinx.ext.intersphinx":1,"sphinx.ext.viewcode":1,sphinx:56},filenames:["CONTRIBUTE.md","advanced_usage.rst","advanced_usage/descriptors.rst","advanced_usage/hyperparameters.rst","advanced_usage/openpmd.rst","advanced_usage/predictions.rst","advanced_usage/trainingmodel.rst","api/mala.rst","api/mala.common.rst","api/mala.common.check_modules.rst","api/mala.common.json_serializable.rst","api/mala.common.parallelizer.rst","api/mala.common.parameters.rst","api/mala.common.physical_data.rst","api/mala.datageneration.rst","api/mala.datageneration.ofdft_initializer.rst","api/mala.datageneration.trajectory_analyzer.rst","api/mala.datahandling.rst","api/mala.datahandling.data_converter.rst","api/mala.datahandling.data_handler.rst","api/mala.datahandling.data_handler_base.rst","api/mala.datahandling.data_repo.rst","api/mala.datahandling.data_scaler.rst","api/mala.datahandling.data_shuffler.rst","api/mala.datahandling.fast_tensor_dataset.rst","api/mala.datahandling.lazy_load_dataset.rst","api/mala.datahandling.lazy_load_dataset_single.rst","api/mala.datahandling.multi_lazy_load_data_loader.rst","api/mala.datahandling.snapshot.rst","api/mala.descriptors.rst","api/mala.descriptors.atomic_density.rst","api/mala.descriptors.bispectrum.rst","api/mala.descriptors.descriptor.rst","api/mala.descriptors.lammps_utils.rst","api/mala.descriptors.minterpy_descriptors.rst","api/mala.interfaces.rst","api/mala.interfaces.ase_calculator.rst","api/mala.network.rst","api/mala.network.acsd_analyzer.rst","api/mala.network.hyper_opt.rst","api/mala.network.hyper_opt_naswot.rst","api/mala.network.hyper_opt_oat.rst","api/mala.network.hyper_opt_optuna.rst","api/mala.network.hyperparameter.rst","api/mala.network.hyperparameter_acsd.rst","api/mala.network.hyperparameter_naswot.rst","api/mala.network.hyperparameter_oat.rst","api/mala.network.hyperparameter_optuna.rst","api/mala.network.multi_training_pruner.rst","api/mala.network.naswot_pruner.rst","api/mala.network.network.rst","api/mala.network.objective_base.rst","api/mala.network.objective_naswot.rst","api/mala.network.predictor.rst","api/mala.network.runner.rst","api/mala.network.tester.rst","api/mala.network.trainer.rst","api/mala.targets.rst","api/mala.targets.atomic_force.rst","api/mala.targets.calculation_helpers.rst","api/mala.targets.cube_parser.rst","api/mala.targets.density.rst","api/mala.targets.dos.rst","api/mala.targets.ldos.rst","api/mala.targets.target.rst","api/mala.targets.xsf_parser.rst","api/mala.version.rst","api/modules.rst","basic_usage.rst","basic_usage/hyperparameters.rst","basic_usage/more_data.rst","basic_usage/predictions.rst","basic_usage/trainingmodel.rst","citing.rst","index.md","install/installing_lammps.rst","install/installing_mala.rst","install/installing_qe.rst","installation.rst"],objects:{"":[[7,0,0,"-","mala"]],"mala.common":[[9,0,0,"-","check_modules"],[10,0,0,"-","json_serializable"],[11,0,0,"-","parallelizer"],[12,0,0,"-","parameters"],[13,0,0,"-","physical_data"]],"mala.common.check_modules":[[9,1,1,"","check_modules"]],"mala.common.json_serializable":[[10,2,1,"","JSONSerializable"]],"mala.common.json_serializable.JSONSerializable":[[10,3,1,"","from_json"],[10,3,1,"","to_json"]],"mala.common.parallelizer":[[11,1,1,"","barrier"],[11,1,1,"","finalize"],[11,1,1,"","get_comm"],[11,1,1,"","get_local_rank"],[11,1,1,"","get_rank"],[11,1,1,"","get_size"],[11,1,1,"","parallel_warn"],[11,1,1,"","printout"],[11,1,1,"","set_current_verbosity"],[11,1,1,"","set_ddp_status"],[11,1,1,"","set_lammps_instance"],[11,1,1,"","set_mpi_status"]],"mala.common.parameters":[[12,2,1,"","Parameters"],[12,2,1,"","ParametersBase"],[12,2,1,"","ParametersData"],[12,2,1,"","ParametersDataGeneration"],[12,2,1,"","ParametersDescriptors"],[12,2,1,"","ParametersHyperparameterOptimization"],[12,2,1,"","ParametersNetwork"],[12,2,1,"","ParametersRunning"],[12,2,1,"","ParametersTargets"]],"mala.common.parameters.Parameters":[[12,4,1,"","comment"],[12,4,1,"","data"],[12,4,1,"","debug"],[12,4,1,"","descriptors"],[12,5,1,"","device"],[12,4,1,"","hyperparameters"],[12,3,1,"","load_from_file"],[12,3,1,"","load_from_json"],[12,3,1,"","load_from_pickle"],[12,4,1,"","manual_seed"],[12,4,1,"","network"],[12,5,1,"","openpmd_configuration"],[12,5,1,"","openpmd_granularity"],[12,3,1,"","optuna_singlenode_setup"],[12,4,1,"","running"],[12,3,1,"","save"],[12,3,1,"","save_as_json"],[12,3,1,"","save_as_pickle"],[12,3,1,"","show"],[12,4,1,"","targets"],[12,5,1,"","use_ddp"],[12,5,1,"","use_gpu"],[12,5,1,"","use_lammps"],[12,5,1,"","use_mpi"],[12,5,1,"","verbosity"]],"mala.common.parameters.ParametersBase":[[12,3,1,"","from_json"],[12,3,1,"","show"],[12,3,1,"","to_json"]],"mala.common.parameters.ParametersData":[[12,4,1,"","data_splitting_type"],[12,4,1,"","descriptors_contain_xyz"],[12,4,1,"","input_rescaling_type"],[12,4,1,"","output_rescaling_type"],[12,4,1,"","shuffling_seed"],[12,4,1,"","snapshot_directories_list"],[12,4,1,"","use_fast_tensor_data_set"],[12,4,1,"","use_lazy_loading"],[12,4,1,"","use_lazy_loading_prefetch"]],"mala.common.parameters.ParametersDataGeneration":[[12,4,1,"","local_psp_name"],[12,4,1,"","local_psp_path"],[12,4,1,"","ofdft_friction"],[12,4,1,"","ofdft_kedf"],[12,4,1,"","ofdft_number_of_timesteps"],[12,4,1,"","ofdft_temperature"],[12,4,1,"","ofdft_timestep"],[12,4,1,"","trajectory_analysis_below_average_counter"],[12,4,1,"","trajectory_analysis_correlation_metric_cutoff"],[12,4,1,"","trajectory_analysis_denoising_width"],[12,4,1,"","trajectory_analysis_estimated_equilibrium"],[12,4,1,"","trajectory_analysis_temperature_tolerance_percent"]],"mala.common.parameters.ParametersDescriptors":[[12,4,1,"","atomic_density_sigma"],[12,5,1,"","bispectrum_cutoff"],[12,5,1,"","bispectrum_switchflag"],[12,4,1,"","bispectrum_twojmax"],[12,4,1,"","descriptor_type"],[12,4,1,"","descriptors_contain_xyz"],[12,4,1,"","lammps_compute_file"],[12,5,1,"","use_y_splitting"],[12,5,1,"","use_z_splitting"]],"mala.common.parameters.ParametersHyperparameterOptimization":[[12,4,1,"","direction"],[12,4,1,"","hlist"],[12,4,1,"","n_trials"],[12,5,1,"","number_training_per_trial"],[12,5,1,"","rdb_storage_heartbeat"],[12,3,1,"","show"],[12,5,1,"","trial_ensemble_evaluation"]],"mala.common.parameters.ParametersNetwork":[[12,4,1,"","nn_type"]],"mala.common.parameters.ParametersRunning":[[12,5,1,"","after_before_training_metric"],[12,4,1,"","checkpoint_name"],[12,4,1,"","checkpoints_each_epoch"],[12,5,1,"","during_training_metric"],[12,4,1,"","early_stopping_epochs"],[12,4,1,"","early_stopping_threshold"],[12,4,1,"","inference_data_grid"],[12,4,1,"","learning_rate"],[12,4,1,"","learning_rate_decay"],[12,4,1,"","learning_rate_patience"],[12,4,1,"","learning_rate_scheduler"],[12,4,1,"","max_number_epochs"],[12,4,1,"","mini_batch_size"],[12,4,1,"","num_workers"],[12,4,1,"","profiler_range"],[12,4,1,"","training_report_frequency"],[12,4,1,"","trainingtype"],[12,5,1,"","use_graphs"],[12,4,1,"","use_mixed_precision"],[12,4,1,"","use_shuffling_for_samplers"],[12,4,1,"","visualisation"],[12,4,1,"","visualisation_dir"],[12,4,1,"","visualisation_dir_append_date"],[12,4,1,"","weight_decay"]],"mala.common.parameters.ParametersTargets":[[12,4,1,"","ldos_gridoffset_ev"],[12,4,1,"","ldos_gridsize"],[12,4,1,"","ldos_gridspacing_ev"],[12,4,1,"","pseudopotential_path"],[12,4,1,"","rdf_parameters"],[12,5,1,"","restrict_targets"],[12,4,1,"","ssf_parameters"],[12,4,1,"","target_type"],[12,4,1,"","tpcf_parameters"]],"mala.common.physical_data":[[13,2,1,"","PhysicalData"]],"mala.common.physical_data.PhysicalData":[[13,2,1,"","SkipArrayWriting"],[13,5,1,"","data_name"],[13,5,1,"","feature_size"],[13,3,1,"","read_dimensions_from_numpy_file"],[13,3,1,"","read_dimensions_from_openpmd_file"],[13,3,1,"","read_from_numpy_file"],[13,3,1,"","read_from_openpmd_file"],[13,5,1,"","si_dimension"],[13,5,1,"","si_unit_conversion"],[13,3,1,"","write_to_numpy_file"],[13,3,1,"","write_to_openpmd_file"],[13,3,1,"","write_to_openpmd_iteration"]],"mala.datageneration":[[15,0,0,"-","ofdft_initializer"],[16,0,0,"-","trajectory_analyzer"]],"mala.datageneration.ofdft_initializer":[[15,2,1,"","OFDFTInitializer"]],"mala.datageneration.ofdft_initializer.OFDFTInitializer":[[15,3,1,"","get_equilibrated_configuration"]],"mala.datageneration.trajectory_analyzer":[[16,2,1,"","TrajectoryAnalyzer"]],"mala.datageneration.trajectory_analyzer.TrajectoryAnalyzer":[[16,5,1,"","first_snapshot"],[16,3,1,"","get_first_snapshot"],[16,3,1,"","get_snapshot_correlation_cutoff"],[16,3,1,"","get_uncorrelated_snapshots"],[16,5,1,"","snapshot_correlation_cutoff"],[16,5,1,"","trajectory"],[16,3,1,"","uncache_properties"]],"mala.datahandling":[[18,0,0,"-","data_converter"],[19,0,0,"-","data_handler"],[20,0,0,"-","data_handler_base"],[21,0,0,"-","data_repo"],[22,0,0,"-","data_scaler"],[23,0,0,"-","data_shuffler"],[24,0,0,"-","fast_tensor_dataset"],[25,0,0,"-","lazy_load_dataset"],[26,0,0,"-","lazy_load_dataset_single"],[27,0,0,"-","multi_lazy_load_data_loader"],[28,0,0,"-","snapshot"]],"mala.datahandling.data_converter":[[18,2,1,"","DataConverter"]],"mala.datahandling.data_converter.DataConverter":[[18,3,1,"","add_snapshot"],[18,3,1,"","convert_snapshots"],[18,4,1,"","descriptor_calculator"],[18,4,1,"","target_calculator"]],"mala.datahandling.data_handler":[[19,2,1,"","DataHandler"]],"mala.datahandling.data_handler.DataHandler":[[19,3,1,"","clear_data"],[19,3,1,"","get_snapshot_calculation_output"],[19,3,1,"","get_test_input_gradient"],[19,3,1,"","mix_datasets"],[19,3,1,"","prepare_data"],[19,3,1,"","prepare_for_testing"],[19,3,1,"","raw_numpy_to_converted_scaled_tensor"],[19,3,1,"","resize_snapshots_for_debugging"]],"mala.datahandling.data_handler_base":[[20,2,1,"","DataHandlerBase"]],"mala.datahandling.data_handler_base.DataHandlerBase":[[20,3,1,"","add_snapshot"],[20,3,1,"","clear_data"],[20,5,1,"","input_dimension"],[20,5,1,"","output_dimension"]],"mala.datahandling.data_scaler":[[22,2,1,"","DataScaler"]],"mala.datahandling.data_scaler.DataScaler":[[22,3,1,"","finish_incremental_fitting"],[22,3,1,"","fit"],[22,3,1,"","incremental_fit"],[22,3,1,"","inverse_transform"],[22,3,1,"","load_from_file"],[22,3,1,"","save"],[22,3,1,"","start_incremental_fitting"],[22,3,1,"","transform"]],"mala.datahandling.data_shuffler":[[23,2,1,"","DataShuffler"]],"mala.datahandling.data_shuffler.DataShuffler":[[23,3,1,"","add_snapshot"],[23,3,1,"","shuffle_snapshots"]],"mala.datahandling.fast_tensor_dataset":[[24,2,1,"","FastTensorDataset"]],"mala.datahandling.fast_tensor_dataset.FastTensorDataset":[[24,3,1,"","shuffle"]],"mala.datahandling.lazy_load_dataset":[[25,2,1,"","LazyLoadDataset"]],"mala.datahandling.lazy_load_dataset.LazyLoadDataset":[[25,3,1,"","add_snapshot_to_dataset"],[25,3,1,"","get_new_data"],[25,3,1,"","mix_datasets"],[25,5,1,"","return_outputs_directly"]],"mala.datahandling.lazy_load_dataset_single":[[26,2,1,"","LazyLoadDatasetSingle"]],"mala.datahandling.lazy_load_dataset_single.LazyLoadDatasetSingle":[[26,3,1,"","allocate_shared_mem"],[26,3,1,"","deallocate_shared_mem"],[26,3,1,"","delete_data"],[26,3,1,"","mix_datasets"]],"mala.datahandling.multi_lazy_load_data_loader":[[27,2,1,"","MultiLazyLoadDataLoader"]],"mala.datahandling.multi_lazy_load_data_loader.MultiLazyLoadDataLoader":[[27,3,1,"","cleanup"],[27,3,1,"","load_snapshot_to_shm"]],"mala.datahandling.snapshot":[[28,2,1,"","Snapshot"]],"mala.datahandling.snapshot.Snapshot":[[28,3,1,"","from_json"]],"mala.descriptors":[[30,0,0,"-","atomic_density"],[31,0,0,"-","bispectrum"],[32,0,0,"-","descriptor"],[33,0,0,"-","lammps_utils"],[34,0,0,"-","minterpy_descriptors"]],"mala.descriptors.atomic_density":[[30,2,1,"","AtomicDensity"]],"mala.descriptors.atomic_density.AtomicDensity":[[30,3,1,"","backconvert_units"],[30,3,1,"","convert_units"],[30,5,1,"","data_name"],[30,5,1,"","feature_size"],[30,3,1,"","get_optimal_sigma"]],"mala.descriptors.bispectrum":[[31,2,1,"","Bispectrum"]],"mala.descriptors.bispectrum.Bispectrum":[[31,3,1,"","backconvert_units"],[31,3,1,"","convert_units"],[31,5,1,"","data_name"],[31,5,1,"","feature_size"]],"mala.descriptors.descriptor":[[32,2,1,"","Descriptor"]],"mala.descriptors.descriptor.Descriptor":[[32,3,1,"","backconvert_units"],[32,3,1,"","calculate_from_atoms"],[32,3,1,"","calculate_from_qe_out"],[32,3,1,"","convert_local_to_3d"],[32,3,1,"","convert_units"],[32,5,1,"","descriptors_contain_xyz"],[32,3,1,"","enforce_pbc"],[32,3,1,"","gather_descriptors"],[32,5,1,"","si_dimension"],[32,5,1,"","si_unit_conversion"]],"mala.descriptors.lammps_utils":[[33,1,1,"","extract_compute_np"],[33,1,1,"","set_cmdlinevars"]],"mala.descriptors.minterpy_descriptors":[[34,2,1,"","MinterpyDescriptors"]],"mala.descriptors.minterpy_descriptors.MinterpyDescriptors":[[34,3,1,"","backconvert_units"],[34,3,1,"","convert_units"],[34,5,1,"","data_name"],[34,5,1,"","feature_size"]],"mala.interfaces":[[36,0,0,"-","ase_calculator"]],"mala.interfaces.ase_calculator":[[36,2,1,"","MALA"]],"mala.interfaces.ase_calculator.MALA":[[36,3,1,"","calculate"],[36,3,1,"","calculate_properties"],[36,4,1,"","implemented_properties"],[36,3,1,"","load_model"],[36,3,1,"","save_calculator"]],"mala.network":[[38,0,0,"-","acsd_analyzer"],[39,0,0,"-","hyper_opt"],[40,0,0,"-","hyper_opt_naswot"],[41,0,0,"-","hyper_opt_oat"],[42,0,0,"-","hyper_opt_optuna"],[43,0,0,"-","hyperparameter"],[44,0,0,"-","hyperparameter_acsd"],[45,0,0,"-","hyperparameter_naswot"],[46,0,0,"-","hyperparameter_oat"],[47,0,0,"-","hyperparameter_optuna"],[48,0,0,"-","multi_training_pruner"],[49,0,0,"-","naswot_pruner"],[50,0,0,"-","network"],[51,0,0,"-","objective_base"],[52,0,0,"-","objective_naswot"],[53,0,0,"-","predictor"],[54,0,0,"-","runner"],[55,0,0,"-","tester"],[56,0,0,"-","trainer"]],"mala.network.acsd_analyzer":[[38,2,1,"","ACSDAnalyzer"]],"mala.network.acsd_analyzer.ACSDAnalyzer":[[38,3,1,"","add_hyperparameter"],[38,3,1,"","add_snapshot"],[38,3,1,"","perform_study"],[38,3,1,"","set_optimal_parameters"]],"mala.network.hyper_opt":[[39,2,1,"","HyperOpt"]],"mala.network.hyper_opt.HyperOpt":[[39,3,1,"","add_hyperparameter"],[39,3,1,"","checkpoint_exists"],[39,3,1,"","clear_hyperparameters"],[39,3,1,"","perform_study"],[39,3,1,"","set_optimal_parameters"],[39,3,1,"","set_parameters"]],"mala.network.hyper_opt_naswot":[[40,2,1,"","HyperOptNASWOT"]],"mala.network.hyper_opt_naswot.HyperOptNASWOT":[[40,3,1,"","get_best_trial_results"],[40,3,1,"","perform_study"],[40,3,1,"","set_optimal_parameters"]],"mala.network.hyper_opt_oat":[[41,2,1,"","HyperOptOAT"]],"mala.network.hyper_opt_oat.HyperOptOAT":[[41,3,1,"","add_hyperparameter"],[41,3,1,"","get_best_trial_results"],[41,3,1,"","get_optimal_parameters"],[41,3,1,"","get_orthogonal_array"],[41,3,1,"","load_from_file"],[41,3,1,"","number_of_runs"],[41,3,1,"","perform_study"],[41,3,1,"","resume_checkpoint"],[41,3,1,"","set_optimal_parameters"],[41,3,1,"","show_order_of_importance"]],"mala.network.hyper_opt_optuna":[[42,2,1,"","HyperOptOptuna"]],"mala.network.hyper_opt_optuna.HyperOptOptuna":[[42,3,1,"","get_trials_from_study"],[42,3,1,"","load_from_file"],[42,3,1,"","perform_study"],[42,3,1,"","requeue_zombie_trials"],[42,3,1,"","resume_checkpoint"],[42,3,1,"","set_optimal_parameters"]],"mala.network.hyperparameter":[[43,2,1,"","Hyperparameter"]],"mala.network.hyperparameter_acsd":[[44,2,1,"","HyperparameterACSD"]],"mala.network.hyperparameter_naswot":[[45,2,1,"","HyperparameterNASWOT"]],"mala.network.hyperparameter_oat":[[46,2,1,"","HyperparameterOAT"]],"mala.network.hyperparameter_oat.HyperparameterOAT":[[46,3,1,"","get_categorical"],[46,3,1,"","get_parameter"],[46,5,1,"","num_choices"]],"mala.network.hyperparameter_optuna":[[47,2,1,"","HyperparameterOptuna"]],"mala.network.hyperparameter_optuna.HyperparameterOptuna":[[47,3,1,"","get_categorical"],[47,3,1,"","get_float"],[47,3,1,"","get_int"],[47,3,1,"","get_parameter"]],"mala.network.multi_training_pruner":[[48,2,1,"","MultiTrainingPruner"]],"mala.network.multi_training_pruner.MultiTrainingPruner":[[48,3,1,"","prune"]],"mala.network.naswot_pruner":[[49,2,1,"","NASWOTPruner"]],"mala.network.naswot_pruner.NASWOTPruner":[[49,3,1,"","prune"]],"mala.network.network":[[50,2,1,"","FeedForwardNet"],[50,2,1,"","GRU"],[50,2,1,"","LSTM"],[50,2,1,"","Network"],[50,2,1,"","PositionalEncoding"],[50,2,1,"","TransformerNet"]],"mala.network.network.FeedForwardNet":[[50,3,1,"","forward"]],"mala.network.network.GRU":[[50,3,1,"","forward"],[50,3,1,"","init_hidden"]],"mala.network.network.LSTM":[[50,3,1,"","forward"],[50,3,1,"","init_hidden"]],"mala.network.network.Network":[[50,3,1,"","calculate_loss"],[50,3,1,"","do_prediction"],[50,3,1,"","forward"],[50,3,1,"","load_from_file"],[50,3,1,"","save_network"]],"mala.network.network.PositionalEncoding":[[50,3,1,"","forward"]],"mala.network.network.TransformerNet":[[50,3,1,"","forward"],[50,3,1,"","generate_square_subsequent_mask"],[50,3,1,"","init_weights"]],"mala.network.objective_base":[[51,2,1,"","ObjectiveBase"]],"mala.network.objective_base.ObjectiveBase":[[51,3,1,"","parse_trial"],[51,3,1,"","parse_trial_oat"],[51,3,1,"","parse_trial_optuna"]],"mala.network.objective_naswot":[[52,2,1,"","ObjectiveNASWOT"]],"mala.network.predictor":[[53,2,1,"","Predictor"]],"mala.network.predictor.Predictor":[[53,3,1,"","predict_for_atoms"],[53,3,1,"","predict_from_qeout"]],"mala.network.runner":[[54,2,1,"","Runner"]],"mala.network.runner.Runner":[[54,3,1,"","load_run"],[54,3,1,"","run_exists"],[54,3,1,"","save_run"]],"mala.network.tester":[[55,2,1,"","Tester"]],"mala.network.tester.Tester":[[55,3,1,"","predict_targets"],[55,3,1,"","test_all_snapshots"],[55,3,1,"","test_snapshot"]],"mala.network.trainer":[[56,2,1,"","Trainer"]],"mala.network.trainer.Trainer":[[56,3,1,"","load_run"],[56,3,1,"","run_exists"],[56,3,1,"","train_network"]],"mala.targets":[[58,0,0,"-","atomic_force"],[59,0,0,"-","calculation_helpers"],[60,0,0,"-","cube_parser"],[61,0,0,"-","density"],[62,0,0,"-","dos"],[63,0,0,"-","ldos"],[64,0,0,"-","target"],[65,0,0,"-","xsf_parser"]],"mala.targets.atomic_force":[[58,2,1,"","AtomicForce"]],"mala.targets.atomic_force.AtomicForce":[[58,3,1,"","convert_units"],[58,3,1,"","get_feature_size"]],"mala.targets.calculation_helpers":[[59,1,1,"","analytical_integration"],[59,1,1,"","entropy_multiplicator"],[59,1,1,"","fermi_function"],[59,1,1,"","gaussians"],[59,1,1,"","get_beta"],[59,1,1,"","get_f0_value"],[59,1,1,"","get_f1_value"],[59,1,1,"","get_f2_value"],[59,1,1,"","get_s0_value"],[59,1,1,"","get_s1_value"],[59,1,1,"","integrate_values_on_spacing"]],"mala.targets.cube_parser":[[60,2,1,"","CubeFile"],[60,1,1,"","read_cube"],[60,1,1,"","read_imcube"],[60,1,1,"","write_cube"],[60,1,1,"","write_imcube"]],"mala.targets.cube_parser.CubeFile":[[60,3,1,"","readline"]],"mala.targets.density":[[61,2,1,"","Density"]],"mala.targets.density.Density":[[61,3,1,"","backconvert_units"],[61,3,1,"","convert_units"],[61,5,1,"","data_name"],[61,5,1,"","density"],[61,5,1,"","feature_size"],[61,3,1,"","from_cube_file"],[61,3,1,"","from_ldos_calculator"],[61,3,1,"","from_numpy_array"],[61,3,1,"","from_numpy_file"],[61,3,1,"","from_openpmd_file"],[61,3,1,"","from_xsf_file"],[61,3,1,"","get_atomic_forces"],[61,3,1,"","get_density"],[61,3,1,"","get_energy_contributions"],[61,3,1,"","get_number_of_electrons"],[61,3,1,"","get_scaled_positions_for_qe"],[61,3,1,"","get_target"],[61,3,1,"","invalidate_target"],[61,5,1,"","number_of_electrons"],[61,3,1,"","read_from_array"],[61,3,1,"","read_from_cube"],[61,3,1,"","read_from_xsf"],[61,5,1,"","si_dimension"],[61,5,1,"","si_unit_conversion"],[61,4,1,"","te_mutex"],[61,5,1,"","total_energy_contributions"],[61,3,1,"","uncache_properties"],[61,3,1,"","write_to_cube"],[61,3,1,"","write_to_openpmd_file"]],"mala.targets.dos":[[62,2,1,"","DOS"]],"mala.targets.dos.DOS":[[62,3,1,"","backconvert_units"],[62,5,1,"","band_energy"],[62,3,1,"","convert_units"],[62,5,1,"","data_name"],[62,5,1,"","density_of_states"],[62,5,1,"","energy_grid"],[62,5,1,"","entropy_contribution"],[62,5,1,"","feature_size"],[62,5,1,"","fermi_energy"],[62,3,1,"","from_ldos_calculator"],[62,3,1,"","from_numpy_array"],[62,3,1,"","from_numpy_file"],[62,3,1,"","from_qe_dos_txt"],[62,3,1,"","from_qe_out"],[62,3,1,"","get_band_energy"],[62,3,1,"","get_density_of_states"],[62,3,1,"","get_energy_grid"],[62,3,1,"","get_entropy_contribution"],[62,3,1,"","get_number_of_electrons"],[62,3,1,"","get_self_consistent_fermi_energy"],[62,3,1,"","get_target"],[62,3,1,"","invalidate_target"],[62,5,1,"","number_of_electrons"],[62,3,1,"","read_from_array"],[62,3,1,"","read_from_qe_dos_txt"],[62,3,1,"","read_from_qe_out"],[62,5,1,"","si_dimension"],[62,5,1,"","si_unit_conversion"],[62,3,1,"","uncache_properties"]],"mala.targets.ldos":[[63,2,1,"","LDOS"]],"mala.targets.ldos.LDOS":[[63,3,1,"","backconvert_units"],[63,5,1,"","band_energy"],[63,3,1,"","convert_units"],[63,5,1,"","data_name"],[63,5,1,"","density"],[63,5,1,"","density_of_states"],[63,5,1,"","energy_grid"],[63,5,1,"","entropy_contribution"],[63,5,1,"","feature_size"],[63,5,1,"","fermi_energy"],[63,3,1,"","from_cube_file"],[63,3,1,"","from_numpy_array"],[63,3,1,"","from_numpy_file"],[63,3,1,"","from_openpmd_file"],[63,3,1,"","from_xsf_file"],[63,3,1,"","get_atomic_forces"],[63,3,1,"","get_band_energy"],[63,3,1,"","get_density"],[63,3,1,"","get_density_of_states"],[63,3,1,"","get_energy_grid"],[63,3,1,"","get_entropy_contribution"],[63,3,1,"","get_number_of_electrons"],[63,3,1,"","get_self_consistent_fermi_energy"],[63,3,1,"","get_target"],[63,3,1,"","get_total_energy"],[63,3,1,"","invalidate_target"],[63,5,1,"","local_density_of_states"],[63,5,1,"","number_of_electrons"],[63,3,1,"","read_from_array"],[63,3,1,"","read_from_cube"],[63,3,1,"","read_from_xsf"],[63,5,1,"","si_dimension"],[63,5,1,"","si_unit_conversion"],[63,5,1,"","total_energy"],[63,3,1,"","uncache_properties"]],"mala.targets.target":[[64,2,1,"","Target"]],"mala.targets.target.Target":[[64,3,1,"","backconvert_units"],[64,3,1,"","convert_units"],[64,5,1,"","feature_size"],[64,3,1,"","get_energy_grid"],[64,3,1,"","get_radial_distribution_function"],[64,3,1,"","get_real_space_grid"],[64,3,1,"","get_static_structure_factor"],[64,3,1,"","get_target"],[64,3,1,"","get_three_particle_correlation_function"],[64,3,1,"","invalidate_target"],[64,5,1,"","qe_input_data"],[64,3,1,"","radial_distribution_function_from_atoms"],[64,3,1,"","read_additional_calculation_data"],[64,3,1,"","restrict_data"],[64,5,1,"","si_dimension"],[64,5,1,"","si_unit_conversion"],[64,3,1,"","static_structure_factor_from_atoms"],[64,3,1,"","three_particle_correlation_function_from_atoms"],[64,3,1,"","write_additional_calculation_data"],[64,3,1,"","write_tem_input_file"],[64,3,1,"","write_to_numpy_file"],[64,3,1,"","write_to_openpmd_file"]],"mala.targets.xsf_parser":[[65,1,1,"","read_xsf"]],mala:[[8,0,0,"-","common"],[14,0,0,"-","datageneration"],[17,0,0,"-","datahandling"],[29,0,0,"-","descriptors"],[35,0,0,"-","interfaces"],[37,0,0,"-","network"],[57,0,0,"-","targets"],[66,0,0,"-","version"]]},objnames:{"0":["py","module","Python module"],"1":["py","function","Python function"],"2":["py","class","Python class"],"3":["py","method","Python method"],"4":["py","attribute","Python attribute"],"5":["py","property","Python property"]},objtypes:{"0":"py:module","1":"py:function","2":"py:class","3":"py:method","4":"py:attribute","5":"py:property"},terms:{"0":[2,5,6,11,12,13,18,22,32,33,36,39,43,44,45,46,47,53,59,61,63,64,69,72,76],"000":[2,74],"00001":72,"0048450":64,"005":69,"01":69,"01070":73,"015":69,"023":73,"030":41,"035120":73,"03610":64,"045008":73,"05":12,"1":[2,5,6,12,20,22,32,36,58,59,60,61,62,63,64,70,72,73],"10":[2,3,12,38,41,64,70,72,73,76],"100":[2,6,12,72,74],"1007":41,"1038":73,"104":73,"1063":64,"108":73,"1088":[38,73],"11":[6,12,70,72],"1103":73,"115":73,"12":[3,5,73],"1234":6,"125146":73,"16":73,"1606":64,"1696":64,"17":[64,73],"1883":12,"1_31":41,"1d":[61,63],"1s":12,"2":[2,5,6,12,33,59,62,64,70,72,77],"20":69,"200":5,"2017":60,"2019":[11,60],"2021":73,"2022":73,"2023":73,"2153":[38,73],"224":5,"25th":60,"2632":[38,73],"2685":12,"27":73,"29500":6,"2mic":64,"3":[2,3,12,20,32,41,61,63,70,73,76],"32":[59,69],"33":59,"36808":41,"39m":77,"3d":[61,63],"4":[2,6,12,13,18,70,72,73,76],"40":72,"400":5,"5":[3,6,12,64,70,72],"500":5,"57":64,"6":64,"64":69,"67637":[70,72],"7":[70,76,77],"8":[12,75],"9":73,"91":[32,70],"94":32,"96":69,"97":32,"978":41,"abstract":[13,39,50,64,73],"boolean":[48,49],"break":32,"case":[6,11,12,13,25,26,41,42,48,53,54,63,64,69,75,77],"class":[0,2,4,5,6,10,11,12,13,15,16,18,19,20,22,23,24,25,26,27,28,29,30,31,32,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,58,60,61,62,63,64,69,70,71,72],"const":60,"default":[4,5,6,11,12,18,19,28,32,33,38,52,53,54,56,62,63,69,70,77],"do":[0,2,3,4,5,7,11,12,19,20,23,25,26,27,30,31,32,34,41,42,50,55,57,59,60,61,63,67,69,70,71,72,75,78],"export":[6,10,12,76,77],"final":[6,11,72],"float":[12,16,30,33,39,43,44,45,46,47,50,53,59,60,62,63,64,69],"function":[0,1,2,3,5,6,8,9,11,12,13,16,17,22,28,30,31,32,33,34,36,41,42,43,49,50,51,52,58,59,61,62,63,64,69,70,71,72,73,74,76,78],"import":[1,2,3,36,41,53,63,64,71,77,78],"int":[11,12,13,15,16,18,19,23,25,26,39,43,44,45,46,47,50,52,55,59,60,61,62,64,69],"long":[6,12],"new":[0,3,6,11,12,23,25,26,33,69,72],"p\u00f6schel":0,"public":[2,3,6,69,70,73],"return":[2,10,11,12,13,16,19,22,28,30,31,32,33,34,39,41,42,43,46,47,48,49,50,53,54,55,56,58,59,60,61,62,63,64,65],"static":[5,12,27,30,31,32,34,42,50,58,60,61,62,63,64],"switch":[2,5,12],"true":[2,3,5,6,12,13,18,19,22,25,26,32,33,39,41,42,53,54,56,59,61,62,63,64,70,72],"try":26,"var":21,"while":[2,6,12,61,63,64,73],A:[0,3,5,6,10,11,12,13,16,20,24,27,28,32,36,40,42,48,49,51,53,55,56,60,61,63,64,69,73,74],AND:[11,42,50,60],AS:[11,60],ASE:[5,13,30,32,36,53,61,62,63,64],As:[2,3,4,5,62,72,76,78],BE:[11,42,60],BUT:[11,60],Be:[6,12,50],By:[0,5,6,11,12,61,62,63,69,70,72],FOR:[11,60],For:[2,3,4,5,12,16,19,26,32,36,42,54,56,63,64,69,70,71,72,74,75,78],IN:[11,60],IS:[11,60],IT:42,If:[0,2,3,4,5,6,12,13,15,16,18,19,20,22,23,25,26,32,33,38,39,41,42,48,49,53,54,55,56,59,60,61,62,63,64,69,70,73,74,75,77],In:[0,2,6,12,13,25,39,42,43,44,45,46,47,48,61,62,63,64,69,70,71,72,75,77],It:[3,6,12,26,53,55,60,61,62,63,64,68,71,72,74],NO:[11,60],NOT:[11,12,42,60],No:[2,6,12,22,36,72],OF:[11,12,15,60,74],OR:[11,60],Of:[6,12,72],On:3,One:[3,5,6,60,69,72],THE:[11,42,60],THEN:42,TO:[4,11,42,60],That:[54,69],The:[0,1,2,3,4,5,6,10,11,12,13,16,18,19,28,30,32,33,38,39,40,41,42,50,52,54,56,59,60,61,62,63,64,65,68,69,70,71,72,73,74,75,76,77,78],Their:70,Then:[2,5],There:[2,62,69,72],These:[2,3,6,18,42,62,69,70,74],To:[2,4,5,6,12,26,50,72,73,74,75,77],WILL:42,WITH:[11,60],Will:[16,33,43,63],With:[5,12,25,36,69],__getitem__:24,_build:76,_xxx:12,ab:64,abc:[13,20,39],abil:6,abl:0,about:[5,60,64],abov:[2,11,12,16,49,60,72],absolut:[50,55],absolute_valu:12,ac9956:[38,73],acceler:[1,3,5,6,68,73,74],acces:61,access:[3,5,6,9,16,21,22,26,36,64,69,70,71,72,74,77,78],accompani:[0,72,78],accord:[2,61,64,69],accordingli:[70,74],account:[64,74],accur:[2,3,6,64,70],accuraci:[3,6,12,41,72],achiev:12,acitv:12,acquaint:74,acquir:71,across:[1,6,12,55,72,73,74],acsd:[2,38,70],acsd_analyz:[7,37,67],acsd_point:2,acsdanalyz:[2,38],action:[11,12,60],activ:[0,3,4,5,6,12,54,69,72,74],actual:[0,6,13,16,25,41,42,50,55,69,72,78],actual_output:55,ad:[6,12,16,20,22,25,33,69,70],adam:[0,12,72],add:[0,2,6,12,18,20,22,23,25,33,38,39,41,69,70,72,73,75,77],add_hyperparamet:[2,38,39,41,69],add_snapshot:[2,4,6,18,20,23,38,69,70,72],add_snapshot_a:20,add_snapshot_to_dataset:25,addit:[0,5,6,12,13,18,36,54,61,64,73,76],addition:[6,72,74],additional_attribut:[13,61,64],additional_calculation_data:[54,72],additional_info_input_:70,additional_info_input_path:[18,70],additional_info_input_typ:[18,70],additional_info_save_path:[18,23,70],additional_metadata:13,additon:[12,36],aditya95sriram:60,adjust:[5,12,64,69,71],adress:[12,42],advanc:[2,5,68,69,70,71,72,73,74,76],advantag:18,advers:6,advis:[2,5,12,54],affect:[6,18],aforement:3,after:[0,3,6,12,36,70,72,75,76],after_before_training_metr:[3,6,12],afterward:[2,6,25,62,71,72],again:[22,76],against:[48,49],aggres:12,agre:[0,72],aidan:[0,73],aim:[5,6],akin:6,al:42,algorihm:12,algorithm:[6,12,69,74],all:[0,1,2,3,4,5,6,10,11,12,13,16,17,18,19,20,22,23,25,26,28,32,36,39,42,43,51,53,54,55,59,60,61,62,63,64,68,69,70,71,72,76,77,78],all_chang:36,alloc:[2,12,26],allocate_shared_mem:26,allow:[0,4,5,6,12,72,74,76],almost:6,along:[5,59,73,74],alongsid:[4,13,61,63,76],alphabet:0,alreadi:[6,13,54,71,72,76],also:[1,2,4,5,6,10,12,19,41,50,54,68,70,71,72,73,76,78],alter:[3,71],altern:[12,13,42],alternative_storage_path:42,although:[40,61,74],aluminium:74,alwai:[6,11,12,38,39,43,44,45,46,47,63,68,69,70,75],am:32,american:73,among:69,amount:[2,6,23,72],amp:12,an:[0,1,2,3,4,5,6,11,12,13,15,16,19,25,26,28,30,32,33,36,41,42,44,46,47,48,49,50,51,53,54,58,60,61,62,63,64,68,69,70,71,74,75,76,77],analys:40,analysi:[2,4,5,12,16,38,41,42],analyt:[59,62,63],analytical_integr:59,analyz:[16,38],ang:[58,61],angstrom:32,ani:[0,6,11,12,13,16,18,24,25,26,36,48,49,50,60,61,64,69,70,72,73,74],anoth:[3,6,26],anyth:[12,61],anywai:18,ap:73,apart:[6,70],api:[4,71,72,74],apidoc:76,appli:[12,19,22,42,64,72,73],applic:[42,52],approach:[18,25,26,28,39,43,44,45,46,47,73],appropri:[0,6,63,70],approxim:59,apt:77,ar:[0,1,2,3,4,5,6,11,12,13,16,18,19,20,25,26,28,32,39,40,42,43,44,45,46,47,50,52,53,54,55,58,59,60,61,62,63,64,65,68,69,70,71,72,73,74,76,78],arbitrari:64,arbitrarili:6,architectur:[3,37,39,40,42,50,51,69,75,76],archiv:[16,72],arg:[24,25,26,36,48,49,50,60],argdict:33,argument:[6,12,18,33,59,70],aris:[11,60,77],around:2,arrai:[3,12,13,18,19,20,22,23,27,28,30,31,32,33,34,41,46,50,51,53,58,59,60,61,62,63,64,65,76],array_shap:33,articl:[73,74],arxiv:64,as_numpi:22,asap3:64,asap:64,ase:[15,16,30,32,36,53,61,63,64,71],ase_calcul:[7,35,67],aspect:72,assert:74,assign:[6,12,50],associ:[11,60,61,62],assum:[12,13,16,25,26,33,50,59,61,64,68,69,72,77],assumpt:12,asterisk:63,atom:[2,5,6,12,15,16,28,32,36,53,58,60,61,63,64,70,71,72,74,78],atomic_dens:[7,29,67],atomic_density_sigma:12,atomic_forc:[7,57,61,67],atomicdens:30,atomicforc:58,atomist:71,atoms_angstrom:[61,63,64],attach:6,attempt:[4,23,54,56,61,63,64],attent:[12,73],attila:[0,73,74],attribut:[10,12,13,16,21,28,51,61,64],austin:[0,73],author:[11,60,73],automat:[0,3,5,6,12,16,41,50,54,64,76],avail:[0,2,6,9,12,18,32,39,43,44,45,46,47,59,69,70,72,75,76],availab:6,averag:[2,3,12,64,72],avoid:[3,12,26],awar:[5,50,64,75,77],axi:[12,59],b:[59,73,74],back:[12,26,42],backbon:72,backconvert_unit:[30,31,32,34,61,62,63,64],backend:[5,12],background:3,bad:6,band:[6,12,48,55,62,63,72],band_energi:[3,6,12,48,55,62,63,72],band_energy_ful:55,barrier:11,bartosz:0,base:[0,2,3,4,5,10,12,13,15,16,18,19,20,22,23,24,25,26,27,28,30,31,32,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,58,60,61,62,63,64,69,72,74],baselin:11,baseprun:[48,49],bash:6,basi:[12,60],basic:[2,5,6,68,70,72,74],bat:76,batch:[12,52,69],batch_siz:52,be_dens:5,be_ldo:70,be_model:[71,72],be_shuffl:[4,6],be_snapshot0:[4,6,70,72],be_snapshot1:[2,6,71,72],be_snapshot2:2,be_snapshot:[4,70],becaus:[3,12,36,72],been:[0,2,3,6,22,32,62,70,72,73,74,76,77,78],befor:[0,6,12,48,49,63,64,72,76],behavior:12,being:[5,6,11,25,26,36,54,55,56,61,62,63,72],believ:12,below:[0,12,16,60],benchmark:54,best:[12,40,41,61,69],beta:[59,62],better:6,between:[2,3,6,11,12,16,23,25,42,69],bias:[6,12],bidirect:12,big:[0,64],bigger:12,bin:[12,64,75,77],binari:[70,76],bind:77,bispectrum:[2,7,12,29,32,67,70,71,72,75],bispectrum_cutoff:[2,12,70,72],bispectrum_switchflag:12,bispectrum_twojmax:[2,12,70,72],bit:[12,24,61],black:0,blob:[11,64],bohr:[2,61,63,70],boldsymbol:63,bool:[11,12,13,18,19,22,25,26,32,33,39,41,42,48,49,53,54,56,59,61,62,63,64],both:[2,3,55,60,74],bottleneck:6,bound:[39,43,44,45,47,69],boundari:12,bp:4,branch:75,briefli:6,brillouin:59,broadcast_band_energi:62,broadcast_entropi:62,broadcast_fermi_energi:62,brown:11,brzoza:0,buffer:[26,27],bug:0,bugfix:0,build:[0,4,12,19,68,74],build_fold:75,build_mpi:75,build_shared_lib:75,build_total_energy_energy_modul:77,built:[0,11,75],bump2vers:76,bumpvers:0,busi:6,by_snapshot:12,c:[6,11,60,64],cach:[16,25,26,61,62,63,64],calcul:[0,2,5,6,11,12,13,15,16,18,19,20,22,28,29,30,31,32,33,34,36,38,41,50,52,53,54,55,57,58,59,61,62,63,64,69,70,72,73,74,75,78],calculate_from_atom:32,calculate_from_qe_out:32,calculate_loss:50,calculate_properti:36,calculation_help:[7,57,67],calculation_output:[19,28],calculation_output_fil:20,calculation_typ:64,calibr:[48,49],call:[2,3,6,11,12,13,16,18,24,41,42,49,50,62,64,70,71,72,73,74,78],callow:0,can:[0,2,3,4,5,6,7,9,10,11,12,13,16,18,19,22,25,26,32,36,41,42,50,51,53,54,55,56,64,69,70,71,72,74,75,77,78],candid:[48,49,69],cangi:[0,73,74],cannot:[6,32,61,63],capabilit:2,capabl:[1,3,4,74],care:[6,26,42],categor:[3,12,39,41,43,44,45,46,47,69],categori:11,caus:73,cd:76,cell:[5,12,30,32,36,50,61,63,64],center:[59,74],cento:78,central:[3,50,72],certain:[12,18,39,40,42,62],cff:0,cflag:77,challeng:[73,74],chanc:[3,12],chang:[0,3,4,5,12,36,62,64,75,76,77],changelog:0,chapter:41,character:[12,30],charg:[11,36,60],check:[0,4,6,9,19,22,36,39,48,54,56,75,76],check_modul:[7,8,67],checkout:[21,75,76],checkpoint:[12,36,39,41,42,54,56],checkpoint_exist:[39,56],checkpoint_nam:[3,6,12,39,41,42],checkpoints_each_epoch:[6,12],checkpoints_each_tri:[3,12],chemistri:73,choic:[38,39,41,43,44,45,46,47,52,69,72],choos:[0,2,12],chosen:[2,6,12,70],ci:0,circumv:[6,73],citat:[0,73],cite:74,citeseerx:64,cl:54,claim:[11,60],classic:36,classmethod:[10,12,22,28,36,39,41,42,50,54,56,61,62,63],clean:[42,76],cleanup:27,clear:[0,19,39],clear_data:[19,20],clear_hyperparamet:39,clone:76,cloud:2,cluster:[3,6,42,77],cmake:75,cmake_cxx_compil:75,cmdarg:33,coars:[2,72],code:[3,32,35,64,68,71,73,74,75,76,78],coeffici:72,collabor:0,collect:[3,12,33],collector:36,com:[0,11,12,21,41,60,64,75,76,77],combin:[2,32,36,69],come:[12,32],comm:[11,13],comm_world:11,command:[3,12,33,54,69],comment:12,commit:0,common:[7,11,12,15,16,18,19,20,23,28,30,31,32,34,36,38,39,40,41,42,43,48,49,50,52,53,54,55,56,58,61,62,63,64,67],commun:[3,6,11,12,32],compar:[2,12,16,72,74],comparison:64,compat:[3,4,12,21,41,42,50,51,65,71,75],compil:[75,77],complei:60,complet:[6,70],complete_save_path:[6,18,23,70],complex:60,complianc:0,compliant:4,complic:[2,6],compon:[32,70],comprehens:74,compress:4,compuat:64,comput:[1,2,6,12,22,33,68,73,74],computation:[3,5],compute_typ:33,concept:[3,74],concern:37,concert:54,conda:0,condens:70,condit:[3,11,60],conduct:74,config:0,configur:[0,4,12,15,16,32,53,71,72,75,77],confirm:6,conjunct:[3,12],connect:[11,60],consecut:12,conserve_dimens:63,consid:[0,12,19],consist:[18,19,28,60,62,63,69,72,78],consquenc:16,constant:60,constitut:0,construct:[3,12,18,59,64,72,73,74],constructor:60,consult:[0,4],contain:[2,4,10,12,13,20,23,28,29,32,36,40,55,60,61,62,63,64,72],continu:[54,56,76],contract:[11,60],contribut:[12,61,62,63,74],control:[12,25,32,64,72],convent:[39,41,64],convers:[1,13,19,20,23,25,26,27,32,33,58,61,62,63,64,68],convert3dto1d:19,convert:[4,10,12,18,19,30,31,32,33,34,38,58,61,62,63,64,70],convert_local_to_3d:32,convert_snapshot:[4,18,70],convert_to_threedimension:61,convert_unit:[30,31,32,34,58,61,62,63,64],converted_arrai:[30,31,32,34,58,61,62,63,64],converted_tensor:19,convet:[43,44,45,46,47],cooper:6,coordin:[12,32],copi:[11,48,49,54,60,61,62],copyright:[11,60],core:[0,77],correct:[2,5,6,36,43,50,60,61,69,72,76],correctli:[0,61,76],correl:[3,12,16,64],correspond:[6,12,64,69,70],cosin:[2,16],cost:12,costli:74,could:[5,12],count:12,counter:12,cours:[6,12,72],cover:[68,71],covers:[61,63],cpp:64,cppflag:77,cpu:[1,2,3,6,53,54,63,68,75],cpython:77,creat:[5,6,12,13,15,16,18,19,20,23,30,31,32,34,36,38,39,40,41,42,48,49,50,52,53,54,55,56,58,60,61,62,63,64,69,70,71,72,75,76],create_fil:61,create_qe_fil:63,creation:[19,70],critic:72,crucial:4,csv:72,cube:[5,60,61,63,70],cube_pars:[7,57,67],cubefil:60,cubetool:60,cubic:[61,63,64,74],cuda:[6,12,75],current:[0,3,4,5,6,11,12,14,25,26,38,39,40,41,43,46,47,50,51,54,58,59,60,61,62,63,64,70],curv:12,custom:[63,69],cut:12,cutoff:[2,12,16,70],d:[59,62,63,73,74,75],d_model:50,dai:73,damag:[11,60],daniel:[0,11],data:[0,1,3,5,6,7,12,13,14,17,18,19,20,21,22,23,24,25,26,27,28,30,31,32,33,34,36,38,39,40,41,42,50,53,54,55,56,58,59,60,61,62,63,64,65,68,69,71,73,74,78],data_:4,data_convert:[4,7,17,38,67,70],data_handl:[4,5,7,17,36,39,40,41,42,49,51,52,53,54,55,56,63,67,69,71,72],data_handler_bas:[7,17,19,23,67],data_nam:[13,30,31,34,61,62,63],data_path:[2,4,6,70,71,72],data_repo:[7,17,67],data_repo_path:21,data_scal:[7,17,19,25,26,67],data_shuffl:[4,6,7,17,67],data_splitting_typ:12,data_typ:[19,55,64],databas:3,databasenam:3,dataconvert:[2,4,6,18,19,70],dataformat:60,datagener:[7,67],datahandl:[2,3,4,6,7,18,19,23,25,26,27,36,38,39,40,41,42,49,52,53,54,55,56,63,67,69,72],datahandlerbas:[19,20,23],dataload:[25,26],datasampl:[25,26],datascal:[19,22,25,26],dataset:[13,19,24,25,26,27],datashuffl:[4,6,12,23],datashufl:6,datatyp:[39,41,43,44,45,46,47],date:[0,12,60],dayton:73,db:63,dd:[12,63],dd_db:63,ddp:[6,11,22,25,26,54],de:63,de_dd:63,deactivt:69,dead:42,deadlin:0,deal:[11,13,60,72],dealloc:[26,27],deallocate_shared_mem:26,debian:77,debug:[3,12,72,76],decad:73,decai:12,decid:[0,12,69,72],declar:4,decreas:[12,69],deep:[73,74],defin:[12,48,49,59,62,63,71],degre:16,delete_data:26,delta:[59,62],demand:[2,3,12,50],demonstr:[73,74],denois:12,dens_object:61,denser:70,densiti:[2,5,7,12,55,57,58,62,63,67,71,73,74],density_calcul:[5,61],density_data:[61,63],density_of_st:[5,62,63,71],depend:[5,12,13,19,54,56,60,61,63,70,76],depth:[1,69],deriv:[25,26,27,50,63],descent:12,desciptor:32,describ:[13,30,31,34,61,62,63,69],descript:[0,60,69],descriptor:[0,5,7,11,12,18,19,20,23,25,26,27,28,30,31,34,38,53,63,67,70,71,72,74,75],descriptor_calcul:[18,19,20,23,25,26,27,38],descriptor_calculation_kwarg:[18,70],descriptor_dimens:32,descriptor_input_path:[18,38,70],descriptor_input_typ:[18,38,70],descriptor_save_path:[18,23,70],descriptor_typ:[12,70,72],descriptor_unit:[18,38],descriptors_contain_xyz:[12,32],descriptors_np:32,deseri:10,deserialized_object:[10,12,28],design:3,desir:[12,16,19,30,31,32,34,43,50,61,62,63,64,74],despit:73,detail:[2,3,12,18,38,74],determin:[2,3,5,12,16,55,69,70,72],determinist:12,detriment:12,dev:76,develop:[6,70,74,76,78],deviat:[3,12,22,72],devic:12,devis:2,dft:[3,5,6,7,12,15,18,22,28,32,61,62,63,68,70,74],diagnost:12,dicitionari:33,dict:[10,12,13,18,28,33,55,60,61,63,64,65],dictionari:[10,12,13,18,28,32,33,55,61,62,63,64,72],dictionati:[61,63,64],diff:0,differ:[2,5,6,38,42,52,59,61,69],differenti:12,dim:19,dimens:[5,12,13,20,25,26,30,31,32,34,50,58,61,62,63,64,72],dimension:[2,13,62,70],dipol:36,direct:[0,5,12,18,64,71],directli:[0,2,6,11,12,32,50,53,54,61,62,63,64,72],directori:[0,6,12,18,19,20,23,28,32,63,76,77],dirti:0,disabl:[6,12,25,26,54],discontinu:12,discourag:[25,26],discret:[5,61,62,63,70],discuss:[1,2,3,6,70,72,74],disentangl:3,disk:[6,23,63,72],displac:16,distanc:[2,12,16],distance_threshold:16,distinct:[2,39,43,44,45,46,47],distinguish:3,distribut:[3,5,11,12,50,54,60,62,64],distributeddataparallel:6,divid:[5,61],divisor:[12,59],do_predict:50,doc:76,dockerfil:0,docstr:0,document:[0,4,6,11,12,60,71,78],documentari:76,doe:[6,11,12,19,30,31,34,39,40,56,60,61,62,63,69,76],doesn:[60,62],doi:[38,64,73],don:[12,64],done:[0,2,3,5,11,12,32,38,39,40,41,42,53,55,60,61,64,69,70,72],dornheim:74,dos_calcul:62,dos_data:[62,63],dos_object:62,dos_valu:63,dot:60,doubl:[18,33],doubt:32,down:11,download:77,drastic:[6,18],drawback:6,dresden:74,drive:28,driven:[4,72],dropout:[12,50],dtype:[13,60],due:[61,62,63],dummi:60,dure:[0,2,6,11,12,49,52,54,63,64,69,71,72,73,76],during_training_metr:12,dx:73,dynam:[12,55,71,74],e:[1,3,4,5,6,12,13,16,18,19,30,31,32,34,35,36,38,39,40,41,42,43,44,45,46,47,59,61,62,63,64,69,70,71,72,75,76,77,78],e_:61,e_ewald:61,e_grid:[62,63],e_hartre:61,e_rho_times_v_hxc:61,e_xc:61,eac:12,each:[0,2,3,5,12,16,42,48,49,69,70,72,74],earli:12,earlier:64,early_stopping_epoch:[12,69],early_stopping_threshold:12,easi:[3,6,55],easier:[19,71,72],easili:[0,2,3,6,69,72],echo:6,edu:64,effect:[3,6,12,33,54,63,74],effici:[4,5,64,74,78],effort:[0,74],effortlessli:74,eigenvalu:62,either:[0,5,12,13,19,20,23,40,55,59,61,63,64,69,70,72],electron:[5,7,36,55,58,61,62,63,64,70,71,72,73,74],elem_snapshot:18,elimin:3,elli:[0,73,74],els:[3,6],elsewis:[13,16],emploi:[1,6,72,74],empti:[12,65],emul:22,en:41,enabl:[2,3,5,6,53,54,55,70,72,75],encapsul:6,encod:[2,32,51,70,72,78],encourag:4,end:[3,4,11,12,13,16,42,61,62,63,64,69,72],energi:[0,5,6,7,12,36,48,55,59,61,62,63,64,70,71,72,74,78],energy_grid:[5,59,62,63],energy_integration_method:63,energy_unit:59,energygrid:[62,63],enforc:[32,50,64],enforce_pbc:32,enhanc:[0,74],enough:[2,6,12,48,49,70,78],ensur:[0,6,11,12,18,19,61,63,74],enter:63,entir:[5,6,13,19,20,28,32,50,54,70,72],entri:[0,5,12,61,72],entropi:[59,62,63],entropy_contribut:[62,63],entropy_multipl:59,enviro:70,environ:[0,2,6],epoch:[6,12,69],epsilon:[59,62],epsilon_:62,epsilon_f:[59,62,63],eq:[59,64],equal:33,equat:[62,64],equilibr:[12,15,16,74],equilibrated_snapshot:16,equival:62,erro:76,erron:26,error:[5,6,11,12,25,55,61,62,63,76],especi:[3,12,48,78],espresso:[2,5,18,32,61,62,63,64,70,71,78],essenti:[6,12,18,69],establish:6,estim:[12,16],etc:[0,3,10,12,20,28,36,39,43,44,45,46,47,54,69,71,72],euclidean:12,ev:[12,20,32,58,59,61,62,63,64],evalu:[3,5,12,19,63],even:[1,5,6,64,71],evenli:5,event:[11,60],eventu:[36,63],everi:[0,15,63],everyth:[12,37],evid:12,ewald:61,ex01_checkpoint:6,ex01_checkpoint_train:6,ex01_train_network:72,ex02_shuffle_data:6,ex02_test_network:72,ex03_preprocess_data:70,ex03_tensor_board:6,ex04_acsd:2,ex04_hyperparameter_optim:69,ex05_checkpoint:3,ex05_checkpoint_hyperparameter_optim:3,ex05_run_predict:71,ex06_ase_calcul:71,ex06_distributed_hyperparameter_optim:3,ex07_advanced_hyperparameter_optim:3,ex08_visualize_observ:5,exact:[62,63],exactli:[61,62,63],exampl:[0,2,3,4,5,6,21,41,68,69,70,71,72,74,75],example_minimal_number_of_runs_oa:41,except:[3,5,61,64],excess:73,exclud:12,exclus:[5,69],execut:[0,3,22,42,68,75],exhibit:74,exist:[3,6,26,39,54,56,60,62,71],expans:2,expect:[6,12],experi:12,experiment:[12,14,69],experiment_ddmmyi:12,explain:69,explan:69,explicitli:[12,32],explictli:32,explor:74,exploratori:[2,4],expon:59,express:[11,60,62,63],extend:[5,18,69,71,74],extens:[4,6],extent:13,external_modul:77,extra:[0,32],extract:[3,13,33,46,47,61,65],extract_compute_np:33,f0:59,f1:59,f2:59,f2py:61,f90:77,f90exec:77,f:59,facilit:74,factor:[2,5,6,12,41,59,62,64,69],fail:12,fairli:[32,71],falkner18a:12,fals:[2,6,12,13,16,18,19,22,25,32,33,38,39,40,41,42,53,54,56,59,61,63,64],familiar:[3,68,72],far:[12,70],faruk:0,fashion:69,fast:12,fast_tensor_dataset:[7,17,67],faster:[5,6,18,24,32,71,75,77],fasttensordataset:[24,26],featur:[0,3,6,12,13,20,22,30,31,34,58,61,62,63,64,68,69,72,74,78],feature_from:13,feature_s:[13,30,31,34,61,62,63,64],feature_to:13,fed:74,feed:[12,50],feed_forward:12,feedforwardnet:50,fermi:[55,59,62,63,64],fermi_energi:[59,62,63],fermi_energy_self_consist:[62,63],fermi_funct:59,fermi_v:59,fetch:27,few:[3,5,72],feynman:61,ff:0,ff_multiple_layers_count:69,ff_multiple_layers_neuron:69,ff_neurons_lay:69,ff_neurons_layer_001:[39,43,44,45,46,47],ff_neurons_layer_002:[39,43,44,45,46,47],ff_neurons_layer_00:69,ff_neurons_layer_01:69,ff_neurons_layer_xx:69,ff_neurons_layer_xxx:12,fflag:77,fiedler:[0,73,74],field:70,file:[0,3,4,5,6,10,11,12,13,15,16,18,19,20,22,23,25,26,27,28,32,36,41,42,50,53,54,56,60,61,62,63,64,65,69,70,72,74,76,77],file_based_commun:[18,38],file_index:25,file_nam:61,file_path:[41,42],filenam:[4,12,22,36,60,65],filename_uncorrelated_snapshot:16,filepath:64,fill:[12,15,69,70],find:[0,6,41,73,77],fine:[6,12,70],fingerprint:[12,18,32,38],finish:[6,42],finish_incremental_fit:22,finit:[73,74],first:[2,5,12,16,18,48,49,61,69,70,71,72,74,76,78],first_snapshot:16,firstli:[2,69,72],fit:[11,22,60],fix:[0,76],flag:72,flexibl:64,fname:60,focu:74,folder:[0,12,75,76],follow:[0,1,6,11,12,39,41,43,44,45,46,47,59,60,61,68,69,71,72,74,76],footprint:[12,63],forc:[7,36,58,61,63],force_no_ddp:12,forgiv:12,fork:0,form:[0,12,60,61,71],formal:[4,6],format:[5,12,13,22,32,43,52,56,60,61,62,63,64,65,70,71,72],former:1,formerli:12,formula:59,fortran:61,forward:[12,50,52],found:[3,6,12,38,39,40,41,42],fourier:[12,64],fourier_transform:64,fox:0,fp32:18,fpic:77,frac:[59,63],fraction:12,framework:[3,7,13,50,72],franz:0,free:[3,11,26,60,73,74,78],freedom:22,friction:12,from:[0,2,3,4,5,6,10,11,12,13,16,22,25,26,28,32,33,36,40,41,42,46,47,50,52,53,54,56,59,60,61,62,63,64,65,70,71,72,76],from_cube_fil:[61,63],from_json:[10,12,28],from_ldos_calcul:[5,61,62],from_numpy_arrai:[61,62,63],from_numpy_fil:[61,62,63],from_openpmd_fil:[61,63],from_qe_dos_txt:62,from_qe_out:62,from_xsf_fil:[61,63],front:12,frozentri:[42,48,49],full:[4,6,38,72,75,77],full_visualization_path:6,fulli:[3,4,19],function_valu:59,fundament:0,furnish:[11,60],further:[0,3,4,5,6,12,54,56,69,70,71,72,73,74,75],furthermor:[4,78],futur:[62,72],g:[3,4,5,6,12,13,16,18,30,31,32,34,35,36,39,43,44,45,46,47,61,62,63,64,69,70,71,72,73,74,75,76,77,78],gabriel:[0,73],gain:73,gather:[18,24,32,53,63,72],gather_dens:63,gather_descriptor:32,gather_do:63,gather_ldo:53,gaussian:[12,30,34,59,60],gcc:[75,77],gener:[0,2,5,6,8,11,12,13,14,16,18,41,50,61,62,63,64,68,71,72,73,77],generate_square_subsequent_mask:50,get:[5,11,12,13,19,30,31,32,34,40,41,43,46,53,55,58,59,61,62,63,64,71,72,74],get_atomic_forc:[61,63],get_band_energi:[62,63],get_best_trial_result:[40,41],get_beta:59,get_categor:[46,47],get_comm:11,get_dens:[61,63],get_density_of_st:[62,63],get_energy_contribut:61,get_energy_grid:[62,63,64],get_entropy_contribut:[62,63],get_equilibrated_configur:15,get_f0_valu:59,get_f1_valu:59,get_f2_valu:59,get_feature_s:58,get_first_snapshot:16,get_float:47,get_int:47,get_local_rank:11,get_new_data:25,get_number_of_electron:[61,62,63],get_optimal_paramet:41,get_optimal_sigma:30,get_orthogonal_arrai:41,get_paramet:[46,47],get_potential_energi:71,get_radial_distribution_funct:64,get_rank:11,get_real_space_grid:64,get_s0_valu:59,get_s1_valu:59,get_scaled_positions_for_q:61,get_self_consistent_fermi_energi:[62,63],get_siz:11,get_snapshot_calculation_output:19,get_snapshot_correlation_cutoff:16,get_static_structure_factor:64,get_target:[61,62,63,64],get_test_input_gradi:19,get_three_particle_correlation_funct:64,get_total_energi:63,get_trials_from_studi:42,get_uncorrelated_snapshot:16,git:[0,75,76],github:[0,11,12,21,73,75,76],gitlab:[64,77],give:[1,3,6,12,16,63,68,69,70,72,75],given:[0,6,13,18,32,53,56,59,60,61,62,63,64,69,70,74,78],glimps:72,gmail:60,gnn:0,gnu:77,go:12,goal:65,goe:12,goo:11,good:[2,3,6,12,48,49],got:0,govern:[69,70],gpaw:71,gpu:[0,3,11,12,54,68,75],gradient:[12,19,25,26,69],grand:73,grant:[11,60],granular:70,graph:[6,12],grate:0,gre:6,greater:12,greatli:[12,72],grid:[0,5,12,30,32,59,61,62,63,64,70,72,74,78],grid_dimens:[32,61,64],grid_integration_method:63,gridi:[61,63],gridpoint:61,gridsiz:[12,61,63],gridspac:12,gridx:[61,63],gridz:[61,63],ground:72,grow:73,gru:[12,50],guarante:6,guess:64,gui:4,guid:[1,2,5,68,69,70,71,72,74],guidelin:0,h5:[4,13,61,64],h:[61,75],ha:[0,2,4,5,6,11,12,13,22,25,33,36,41,42,48,49,50,53,54,61,62,63,69,70,72,73,74,76,77,78],hacki:12,had:[6,70],hand:[5,12,13],handl:[3,4,6,17,19,20,23,64,76],handler:[41,42,54,56,63],happen:62,har:74,hard:28,hardwar:[1,5,68],haswel:75,have:[0,2,3,5,6,10,12,13,22,25,26,28,30,31,32,34,38,39,42,43,44,45,46,47,59,62,63,64,69,70,71,72,73,75,76,77,78],haven:76,head:[0,6,12],heartbeat:12,heavi:[5,64],hellman:61,helmholtz:74,help:[3,12,53,63,68,72],helper:[4,59],here:[3,6,12,16,18,25,26,38,41,50,54,62,69,70,71,72,75],herebi:[11,60],hidden:[12,50,69],hierarchi:13,high:[11,12,39,43,44,45,46,47,73],higher:[12,39,43,44,45,47],highli:[2,4,5,6,14,76,78],hint:6,histogram:[12,64],hiwonjoon:11,hlist:12,hoc:16,hoffmann:[0,73,74],hold:[6,12,19,32,39,40,41,42,53,54,55,56,63],holder:[11,60],horovod:0,hossein:0,host:6,hostnam:6,hotyp:[43,44,45,46,47],how:[2,3,12,22,62,63,64,68,69,70,72,75],howev:[2,4,6,12,26,32,52,63,72,73],hpc:[3,6,12,42,77],html:[12,41,76],http:[0,11,12,21,41,60,64,73,75,76,77],huge:6,hundr:[5,74],hyper_opt:[7,37,38,40,41,42,67],hyper_opt_method:[3,12],hyper_opt_naswot:[7,37,67],hyper_opt_oat:[7,37,67],hyper_opt_optuna:[7,37,67],hyperopt:[3,38,39,40,41,42,69],hyperoptim:[2,69],hyperoptnaswot:[40,43],hyperoptoat:[40,41,43],hyperoptoptuna:[40,42,43],hyperparam:12,hyperparamet:[0,1,2,7,12,37,38,39,40,41,42,44,45,46,47,49,51,52,56,67,68,72,73,74,76],hyperparameter_acsd:[7,37,67],hyperparameter_naswot:[7,37,67],hyperparameter_oat:[7,37,67],hyperparameter_optuna:[7,37,45,67],hyperparameteracsd:[43,44],hyperparameternaswot:[43,45],hyperparameteroat:[43,46],hyperparameteroptuna:[43,45,47],hyperparemet:12,i0:59,i1:59,i:[1,3,5,6,12,16,18,19,25,32,38,39,40,41,42,62,64,69,72,78],i_0:59,i_1:59,ibrav:61,icml2019:11,idea:6,ideal:[2,13,61,64],identif:74,identifi:69,idx:46,ifnam:60,ignor:[3,12,18,61,64,68,75],ik:62,imag:[60,64],imaginari:60,immens:0,impact:[6,63],imped:12,implement:[0,3,5,6,10,12,13,22,32,36,48,49,50,61,62,63,64,74,78],implemented_properti:36,impli:[11,13,60,64],improv:[0,1,12,23,24,72],in_unit:[30,31,32,34,58,61,62,63,64],includ:[0,4,11,12,19,28,32,40,41,54,60,63,69,70,74],incopor:70,incorpor:64,increas:[3,12],increment:[6,22,72,76],incremental_fit:22,indent:12,index:[46,76],indic:[22,26,48,49,55],indisput:12,individu:[3,6,70,72,74,78],industri:6,inf:12,infer:[0,5,12,53,54,55,60,63,71,72,74],inference_data_grid:[5,12],infinit:48,infint:48,info:[12,18,72],inform:[2,3,4,6,12,13,15,50,62,64,65,70,71,72],infrastructur:[0,6,42],inher:4,inherit:10,init_hidden:50,init_weight:50,initi:[3,13,15,50,70,74],initial_charg:36,initial_magmom:36,initial_setup:[3,6],initialis:50,initil:12,initrang:50,inject:50,input:[12,19,20,22,23,25,26,27,28,50,61,62,63,64,70,72,78],input_data_scal:[19,25,26],input_dimens:[20,25,26,72],input_directori:[20,23],input_fil:[20,23],input_npy_directori:[20,23,28],input_npy_fil:28,input_requires_grad:[25,26],input_rescaling_typ:[12,69,72],input_shm_nam:27,input_unit:[20,28],inputpp:70,insid:[75,76],instal:[0,2,5,6,74],instanc:[2,3,4,11,12,13,15,16,18,32],instanti:[12,50,54,56,72],instead:[2,3,5,25,26,41,49,60,64,68,70],institut:74,instruct:[0,2,5,74,75,77],integ:[5,12,18,47,69],integr:[53,59,61,62,63,71],integral_valu:59,integrate_values_on_spac:59,integration_method:[61,62,63],integration_valu:59,intel:75,intend:4,inter:6,interact:4,interest:[4,5,65,69,71,72],interfac:[0,2,3,7,11,12,13,32,36,43,49,50,53,61,62,63,64,67,69,70,71],interfer:54,interg:[61,63],intern:[13,18,32,53,54,61,64],internal_iteration_numb:[13,61,64],interpret:6,interv:[3,6,12],intra:6,introduc:[12,74],introduct:68,introductori:70,intuit:[2,6],invalid:[61,62,63,64],invalidate_target:[61,62,63,64],inverse_transform:22,investig:[5,19,20,38,39,42,43,44,45,46,47,69],involv:[2,5,6,72],io:[16,41,71],ion:12,ionic:[12,74],iop:73,ish:77,issu:[12,73],ist:64,iter:[12,13,61,64],its:[4,12,19,69,72,74],itself:[3,5,6,12,16,59,64,70,71,72,73,76],j:[60,73,74,77],jacobian:[12,40,52],jame:0,jiang:74,jmax:12,job:[3,12,42],join:[2,70,71,72],jointli:74,jon:[0,74],josh:[0,12],journal:73,json:[10,12,28,36,54,56,64,69,70],json_dict:[10,12,28],json_serializ:[7,8,12,28,43,67],jsonserializ:[10,12,28,43],judg:[6,48,49],jul:73,jun:73,june:60,jupyt:4,just:[0,2,3,4,5,12,26,54,56,71,72,78],justifi:59,k:[5,53,59,62,63,64,70,74],k_:59,keep:[0,12,25,26],kei:60,kept:[12,60],keyword:[6,12,18,71],kind:[11,13,20,23,60],kindli:[0,73],kinet:12,kmax:[5,12,64],known:[6,36],kohn:[73,74],kokko:[5,11,75],kokkos_arch_gpuarch:75,kokkos_arch_hostarch:75,kokkos_arch_hsw:75,kokkos_arch_volta70:75,kokkos_enable_cuda:75,kotik:0,kpoint:[5,64],ks:[61,62,63],kulkarni:0,kwarg:[24,25,26,27,32,36,41,48,49,50,61,63],kyle:[0,73],l2:12,l:[12,73,74,75],label:12,laboratori:74,lammp:[2,5,11,12,32,33,78],lammps_compute_fil:12,lammps_util:[7,29,67],langevin:12,larg:[2,4,5,6,32,64,72,73,74,76],larger:[5,12,13,61,64,73],last:[12,25,26,36,42,61,69,72],last_trial:42,lastli:70,latenc:6,later:[3,6,22,40,63,69],latest:41,latter:[3,13,64,70],lattic:60,launch:[3,6,12],layer:[3,12,21,39,43,44,45,46,47,69,72],layer_activ:[12,69,72],layer_activation_00:69,layer_activation_xxx:12,layer_s:[12,69,72],lazi:[12,22,23,25,26,72],lazili:[12,19],lazy_load_dataset:[7,17,67],lazy_load_dataset_singl:[7,17,67],lazyloaddataset:[25,26],lazyloaddatasetsingl:26,lbla:77,ldo:[2,5,6,7,12,18,53,55,57,58,59,61,62,64,67,70,71,72,74,78],ldos_calcul:[5,63,71],ldos_data:63,ldos_gridoffset_ev:[6,12,70,72],ldos_grids:[6,12,70,72],ldos_gridspacing_ev:[6,12,70,72],ldos_object:[61,62],ldosfil:70,lead:[2,5,12,64,74],leaf:19,leakyrelu:[12,69],learn:[6,7,12,22,64,69,72,73,74],learner:11,learning_r:[12,69,72],learning_rate_decai:[12,69],learning_rate_pati:[12,69],learning_rate_schedul:12,least:64,leastearly_stopping_threshold:12,leav:26,left:[4,27],legaci:[12,36,64],length:[5,50,73,74],lenz:[0,73,74],less:[12,18,64],let:[12,70,72],level:[11,12,21,25,26,41,53,59,62,63,72,73,74],lf:76,lfftw3:77,liabil:[11,60],liabl:[11,60],lib:[75,77],liblammp:75,librari:[3,4,5,6,22,49,69,71,72,75,77,78],licens:[11,60],lie:32,like:[3,5,6,11,26,72,77],likewis:[2,5,6],limit:[3,5,6,11,12,27,49,60,74],line:[4,33,60,72,73],linger:11,link:[11,41,69,73,75],linux:[76,77,78],list:[0,2,4,5,12,13,18,19,20,27,28,32,33,36,38,39,40,41,42,43,44,45,46,47,51,55,60,61,64,72],littl:61,llapack:77,lmkl_core:77,lmkl_intel_lp64:77,lmkl_sequenti:77,lmp:33,load:[12,19,20,22,23,25,26,27,36,39,41,42,50,53,54,56,62,69,71,72,75,77],load_from_fil:[12,22,41,42,50,69],load_from_json:12,load_from_pickl:12,load_model:[36,71],load_run:[3,6,54,56,71,72],load_runn:[54,56],load_snapshot_to_shm:27,load_with_ddp:54,load_with_gpu:54,load_with_mpi:54,loaded_hyperopt:41,loaded_network:[50,54,56],loaded_param:[41,42,54,56],loaded_paramet:12,loaded_train:42,local:[0,3,11,12,32,61,63,74,75],local_density_of_st:[62,63],local_offset:13,local_psp_nam:12,local_psp_path:12,local_rank:6,local_reach:13,locat:[0,12,63],log:[0,15,59],logdir:6,logging_period:15,longer:[0,2,12,19],look:54,loos:64,loss:[6,12,41,48,50,55,69],loss_function_typ:12,loss_val:50,lot:[65,72,78],low:[12,39,43,44,45,46,47,72],lower:[16,39,43,44,45,47,69],lowest:[12,70],lstm:[12,50],m:74,mach:74,machin:[6,72,73,74,75,76,77],maco:[76,78],made:[0,5,71],mae:[55,72],magmom:36,magnitud:73,mai:[2,3,6,12,16,18,59,62,63,69,72,75,76,77],main:77,mainli:4,maintain:[0,6],mainten:[0,74],major:0,make:[0,3,4,5,6,12,52,63,70,72,74,75,76,77],mala:[1,2,3,4,6,8,9,11,12,13,15,16,18,19,20,21,23,25,26,27,28,30,31,32,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,52,53,54,55,56,58,61,62,63,64,66,67,69,70,72,75,77,78],mala_data_repo:[21,76],mala_foundational_pap:73,mala_hyperparamet:73,mala_paramet:[5,71],mala_shuffled_snapshot:23,mala_sizetransf:73,mala_temperaturetransf:73,mala_vi:6,malada_compat:16,manag:[12,24,72],mandatori:40,mani:[0,2,3,12,70,71],manual:[0,5,12,69,77],manual_se:12,map:63,mape:55,mark:42,mask:50,mass:60,massiv:[3,73],master:[0,11,64],master_addr:6,master_port:6,match:[2,13,60,61,62,63,64],mater:74,materi:[5,71,73,74],mathemat:[3,38,59],mathrm:[59,61],matplotlib:5,matrix:61,matter:[5,19,73,74],max:[12,22,72],max_len:50,max_number_epoch:[12,72],maxim:12,maximum:[2,3,5,12,50,64],mc:[12,35,36],md:[12,15,16,35,36,64,74],mean:[6,12,13,22,32,48,49,52,58,61,62,63,69,70,72],mean_std:12,meaning:[12,64],measur:72,mechan:[18,49,74],medium:12,melt:74,member:[16,64],memori:[6,11,12,18,25,26,27,33,54,56,61,62,63,72],mention:[2,5,6],merchant:[11,60],merg:[0,11,60],merit:71,mess:42,messag:[1,11],meta:[13,60,65],metadata:[4,13,18,26,30,31,34,60,61,62,63,65],metadata_input_path:18,metadata_input_typ:18,method:[0,2,3,5,6,10,12,48,49,50,59,60,61,62,63,64,70,73,74,76],metric:[3,12,16,48,74],mev:6,mic:64,might:[12,26,36,42,50,52],miller:[0,73,74],mimic:60,min:[12,22,72],min_verbos:11,mini:[12,52,69],mini_batch_s:[12,69,72],minim:12,minimum:[11,12,41,64],minor:0,minterpi:0,minterpy_descriptor:[7,29,67],minterpydescriptor:34,minut:5,mit:[11,60],mitig:6,mix:[6,12,19,23,25,26],mix_dataset:[19,25,26],mkl:77,ml:[2,3,5,6,15,58,61,62,63,64,68,70,74],mlr:12,mode:[11,32,54,63,64],model:[0,2,3,5,6,18,36,50,53,54,56,68,69,70,73,74,78],modern:73,modif:[6,64],modifi:[0,11,42,48,49,60,70,77],modin:[0,73,74],modul:[0,6,9,21,50,60,61,64,78],modular:0,moham:[0,73,74],moldabekov:74,molecular:[71,74],moment:[5,12,19,39,43,44,45,46,47],monitor:6,month:73,more:[1,2,3,5,6,12,22,24,36,59,64,70,71,74],moreov:74,most:[2,6,12,54,73,74,75,76,77,78],move:[12,73],mpi4pi:32,mpi:[2,3,5,11,12,18,53,54,63,75,77],mpi_util:11,mpif90:77,mpirun:3,mse:[12,55],much:[6,26,62],mujoco:11,multi:[5,12],multi_lazy_load_data_load:[7,17,67],multi_train:12,multi_training_prun:[7,37,67],multilazyloaddataload:27,multipl:[1,2,3,6,11,12,16,19,20,27,28,32,39,43,44,45,46,47,48,53,59,63,69,70,72],multiple_gaussian:59,multipli:12,multiplicator_v:59,multitrainingprun:48,multivari:12,must:[12,20,63],mutat:33,mutual:[5,69],my:32,my_modified_fil:0,my_studi:3,myriad:73,mysql:3,n:[3,6,61,73,74],n_trial:[12,69],na:12,naiv:6,name:[0,3,6,12,13,16,18,19,23,27,32,33,36,38,39,41,42,43,44,45,46,47,54,56,61,63,64,69,70,72,75,77],naming_schem:[4,18,70],naming_scheme_input:19,naming_scheme_output:19,naswot:[0,3,12,43,45,48,49],naswot_prun:[7,37,67],naswot_pruner_batch_s:12,naswot_pruner_cutoff:12,naswotprun:49,nation:74,natom:61,natur:[0,12],nccl:6,ndarrai:[13,55,61,62,63,64],ndarri:13,necessari:[3,4,6,10,12,18,22,42,64,68,69,70,71,72,75],necessarili:[61,62,63,64],need:[2,5,6,10,12,13,19,20,25,28,32,36,50,54,56,59,61,62,63,64,70,72,75,76,77,78],neg:[6,12,64],neglect:12,neighbor:64,neighborhood:16,neither:63,net:[12,50,60],netwok:12,network:[3,6,7,12,19,22,36,38,39,40,41,42,44,45,46,47,48,49,51,52,53,54,55,56,63,67,69,71,72,73,74],neural:[3,12,36,50,53,55,56,72,73,74],neuron:[12,69,72],new_atom:32,new_datahandl:[41,42,54,56],new_hyperopt:[41,42],new_inst:11,new_runn:54,new_train:56,new_valu:11,newer:77,newli:[54,56,70],next:[6,42,60],nil:[0,73],nn:[3,5,6,50,52,64,69,72],nn_type:12,no_data:[41,42],no_hidden_st:12,no_snapshot:12,node:[6,11,12,42],nodelist:6,nois:12,nomenclatur:69,non:[2,4,61,64],none:[12,13,15,16,18,19,20,22,23,28,30,31,32,33,34,36,38,39,40,41,42,43,44,45,46,47,52,53,54,56,61,62,63,64,72],noninfring:[11,60],nor:63,normal:[12,13,22,72],normand:[0,73],note:[0,5,6,12,26,33,38,39,41,42,43,44,45,46,47,49,59,71,75],notebook:[4,41],noteworthi:69,noth:[5,30,31,34],notic:[11,60],now:[4,6,27,63,65,69,70,71,72,77],np:[3,13,19,59,60,63],npj:[73,74],npy:[2,4,6,18,70,72],nsy:12,ntask:6,num_choic:46,num_head:12,num_hidden_lay:12,num_work:[6,12],number:[0,3,5,6,11,12,13,16,18,19,23,33,36,41,46,55,60,61,62,63,64,66,69,70,72,73,74,77],number_bad_trials_befor:12,number_bad_trials_before_stop:12,number_of_bin:[5,12,64],number_of_electron:[55,61,62,63,72],number_of_nod:6,number_of_run:41,number_of_shuffled_snapshot:[6,23],number_of_tasks_per_nod:6,number_training_per_tri:[3,12],numer:[12,13,16,25,32,39,43,44,45,47,60,61,62,63,64],numpag:73,numpi:[0,2,4,13,18,19,20,22,23,26,27,28,30,31,32,33,34,46,51,53,55,58,59,60,61,62,63,64,65,70],numpy_arrai:19,nvcc_wrapper:75,nvidia:[6,75],o:[12,19],oa:[39,41,43,44,45,46,47,51],oapackag:[41,76],oat:[0,3,12,43,46,51,52],object:[0,3,4,5,6,10,12,13,15,16,18,19,20,22,23,26,27,28,30,31,32,33,34,36,38,39,40,41,42,48,49,50,51,52,53,54,55,56,58,60,61,62,63,64,69,70,71,72],objective_bas:[7,37,52,67],objective_naswot:[7,37,67],objectivebas:[51,52],objectivenaswot:52,observ:[55,71,72,74],observables_to_test:[55,72],obtain:[5,11,19,60,76],occur:[42,59,72,76],oct:73,ofdft_frict:12,ofdft_initi:[7,14,67],ofdft_kedf:12,ofdft_number_of_timestep:12,ofdft_temperatur:12,ofdft_timestep:12,ofdftiniti:15,off:[0,12],offer:[4,6,12,65,74],offici:[4,6,12,68,71,75,76],offload:[5,6],often:[6,12],ol:[0,73,74],old:[12,28],omar:0,onc:[0,1,2,3,5,6,42,60,69,70,72],one:[2,3,4,5,6,11,12,16,19,20,23,32,48,53,60,61,62,63,64,69,70,72,74,78],ones:[5,25,26,32,69],ongo:76,onli:[0,1,2,3,5,6,11,12,13,16,18,19,20,22,25,26,28,33,36,41,42,50,53,54,55,59,60,61,62,63,64,65,69,70],onto:0,onward:6,open:[0,4,13,60,76],openmpi:77,openpmd:[0,1,12,13,18,20,23,28,32,61,62,63,64],openpmd_configur:12,openpmd_granular:12,oper:[5,6,11,12,19,20,23,64,70,72,74,76],opt:76,optim:[0,1,2,5,6,12,30,32,38,39,40,41,42,49,51,52,56,64,68,72,73,74,76],optimal_sigma:30,optimizer_dict:56,option1:75,option2:75,option:[3,4,6,9,11,12,13,18,22,26,28,30,31,32,34,38,40,54,56,60,64,69,70,72,73,74,75,78],opttyp:[39,41,43,44,45,46,47],optuna:[3,12,39,41,42,43,44,45,46,47,48,49,51,52,69],optuna_singlenode_setup:[3,12],orbit:74,order:[0,3,6,11,12,13,19,25,26,41,69,70,71,73,76],org:[38,60,64,73],orient:0,origin:[3,11,20,28,33,60,73],orthogon:[3,12,41,46,51,76],os:[2,70,71,72],oscil:16,ot:[25,26],other:[3,6,10,11,16,32,35,60,61,62,64,69,71,74],otherwis:[11,39,56,60],otherwsi:22,our:[4,73],ourselv:22,out:[0,2,4,6,11,19,40,41,53,60,62,64,70,71,72,75,76],out_unit:[30,31,32,34,61,62,63,64],outfil:[32,70],outlin:[6,59],output:[1,2,6,11,12,18,19,20,22,23,25,26,27,28,30,31,32,34,50,55,57,60,61,62,63,64,70,72,76,78],output_data_scal:[19,25,26],output_dimens:[20,25,26,72],output_directori:[20,23],output_fil:[20,23],output_format:[55,72],output_npy_directori:28,output_npy_fil:[20,23,28],output_rescaling_typ:[12,72],output_shm_nam:27,output_unit:[20,28],outsid:[32,63],over:[1,2,64],overal:0,overfit:72,overflow:59,overhead:[3,12,73],overview:[1,6,75],overwrit:[18,23,26],overwritten:[54,60],own:[4,12,50,72],p:[60,73,74,75],packag:[74,75,78],page:73,pairs:60,paper:[41,48,49,73],paral:12,parallel:[0,1,4,7,8,12,22,32,54,63,67,68,74,75],parallel_warn:11,param:[30,31,32,34,36,38,39,40,41,42,50,51,53,54,55,56,58,60,61,62,63,64,69],paramet:[2,3,4,5,6,7,8,10,11,13,15,16,18,19,20,22,23,25,26,27,28,30,31,32,33,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,58,59,60,61,62,63,64,65,67,69,70,71,74],parametersbas:12,parametersdata:12,parametersdatagener:12,parametersdebug:12,parametersdescriptor:[12,38],parametershyperparameteroptim:12,parametersnetwork:12,parametersrun:[12,52],parameterstarget:[12,64],parametr:19,params_format:[54,56],paraview:4,parent:54,pars:[2,12,18,29,30,31,34,38,51,58,61,62,63,65],parse_tri:51,parse_trial_oat:51,parse_trial_optuna:51,parser:[60,64],part:[5,13,60,61,64,72,78],particl:[12,64],particular:[11,48,49,60],partit:55,parvez:[0,73],pass:[0,12,50,53,63],path:[2,6,12,13,16,18,19,21,36,38,41,42,50,53,54,56,61,62,63,64,70,71,72,75,76,77],path_name_schem:63,path_schem:63,path_to_fil:[50,53],path_to_visu:6,patienc:12,paulbourk:60,pavanello:74,pbc:[32,36],peform:12,penalti:12,peopl:0,pep8:0,per:[6,12,32,36,69,72],percent:12,perform:[1,3,5,12,18,19,22,24,26,36,38,39,40,41,42,50,53,59,62,63,64,68,70,71,72,73,74,75,78],perform_studi:[2,38,39,40,41,42,69],permiss:[11,60],permit:[11,60],permut:26,person:[11,60,70],phase:73,phenomena:73,phy:[73,74],phyiscal:6,physic:[2,3,6,12,13,57,64,73],physical_data:[7,8,32,64,67],physicaldata:[13,32,64],physrevb:73,pickl:[12,22,32],pip:76,pipelin:[19,20,23],pkg_kokko:75,pkg_ml:75,pkl:[39,41,42,54,56],place:[22,72],plan:75,plane:5,plateau:[12,69],plea:64,pleas:[0,2,3,4,5,6,12,38,39,41,42,43,44,45,46,47,63,69,71,72,73,74,75,76],plot:[2,5,64],plu:[3,12],plugin:4,pmd:4,point:[2,3,5,6,12,21,25,26,33,54,62,64,70,72,74],popoola:[0,73,74],popular:73,port:6,portion:[11,18,60],pose:74,posit:[7,32,36,50,53,60,61,70,71],positionalencod:50,possibl:[6,12,38,39,43,44,45,46,47,50,62,69],post:[4,28,64,74,78],postgresql:3,postprocess:[7,58,61,62,63,64],potenti:[0,32,69,74],power:[4,6,71],pp:70,pr:0,practic:6,pre:[0,27],precalcul:78,preced:70,precict:[53,55],precis:[6,12,18,33],predict:[6,7,36,50,53,55,63,64,68,72,73,74],predict_for_atom:[5,53,71],predict_from_qeout:53,predict_target:55,predicted_arrai:50,predicted_ldo:53,predicted_output:55,predictor:[5,7,37,54,56,67,71],prefer:[36,70],prefetch:[6,12,26],prepar:[6,13,19,41,42],prepare_data:[19,54,56,69,72],prepare_for_test:19,preprocess:[2,7,12,32,64,70],present:[13,38,39,40,41,42,54,61,64],press:[12,73],previou:[50,71],primari:69,principl:[2,5,39,43,44,45,46,47,72,74],print:[1,3,6,11,12,41],printout:[1,3,11],prior:[0,2,5,6,12],priorli:16,problem:[6,77],problemat:12,proceed:12,process:[0,2,3,4,6,11,12,18,19,22,25,26,28,32,33,38,51,64,70,71,72,73,74,75,77,78],product:[1,4,6,53,72,75],profil:12,profiler_rang:12,progress:[6,63],project:[0,4,21,75,76],proof:74,proper:[61,62,63,73],properli:[0,11,12],properti:[6,10,12,13,16,20,25,28,30,31,32,34,36,46,61,62,63,64,69,71,74],provid:[2,3,5,6,11,12,13,16,18,21,23,38,40,49,59,60,61,62,63,64,65,70,71,72,75,76],prudent:[3,72],prune:[48,49],pruner:[12,48,49],pseudopotenti:[12,61,63,64,71],pseudopotential_path:[12,71],psu:64,publish:[0,11,60,73],pure:[6,45,62],purpos:[2,11,41,42,60],push:0,put:[5,12,19,42,50],pw:[61,70],py:[0,2,3,6,11,71,72,75],pypi:0,pyproject:0,pytest:76,python3:[3,6,75],python:[2,3,4,5,6,19,20,32,33,61,64,71,78],pythonpath:77,pytorch:[12,19,50,54],q:77,qe:[12,32,53,61,62,63,64,77,78],qe_input_data:[61,63,64],qe_out_fil:32,qe_pseudopotenti:[61,63,64],qef:77,qualiti:0,quantif:0,quantit:12,quantiti:[12,16,18,22,55,57,61,62,63,64],quantum:[5,18,32,61,62,63,64,70,71,73,74,78],quantumespresso:64,question:6,queue:42,quick:32,r:[41,60,63,76],race:3,radial:[5,12,64],radial_distribution_funct:64,radial_distribution_function_from_atom:[5,64],radii:[2,5,12,64],radiu:[2,12,64,70],rais:61,rajamanickam:[0,73,74],ram:[6,25,41,42,50,63],random:[6,50],randomli:3,rang:[2,12,22,41,50,72,73,74],rank:[3,6,11,12,32,53,62,63],rapid:74,rate:[6,12,50,69],rather:[3,19,54,61,62,63],raw:[2,18,19,32,70],raw_numpy_to_converted_scaled_tensor:19,rawradialdistribut:64,rdb:[12,42],rdb_storag:[3,12,42],rdb_storage_heartbeat:12,rdf:[5,12,16,36,64],rdf_paramet:12,re:[0,2,19],read:[4,10,12,13,16,22,25,26,28,53,59,60,61,62,63,64,65,71],read_additional_calculation_data:[62,64],read_additional_read_additional_calculation_data:61,read_cub:60,read_dimensions_from_numpy_fil:13,read_dimensions_from_openpmd_fil:13,read_dtyp:13,read_from_arrai:[61,62,63,71],read_from_cub:[61,63],read_from_numpy_fil:13,read_from_openpmd_fil:13,read_from_qe_dos_txt:62,read_from_qe_out:62,read_from_xsf:[61,63],read_imcub:60,read_xsf:65,readi:[70,72],readlin:60,readthedoc:41,real:[22,60,64,69,72,74,78],realist:78,realli:[30,31,34,36],realspac:[5,16],reason:[6,12,19,62,65,72],rebas:0,recap:6,recent:[73,74,75,76,77],recogn:12,recommend:[6,12,16,61,62,63,64,75,78],reconstruct:[41,42,54,56],record:12,recv:32,redistribut:23,reduc:[12,26,63,70],reducelronplateau:12,reduct:12,refer:[2,3,12,61,68,69,70,72,74,75],reference_data:36,reflect:[5,61,63],reformat:0,regain:26,regard:73,regular:[2,3,5,12,52,70],regularli:0,reimplement:10,rel:[26,50,62],relat:[3,12,75],releas:77,relev:[2,4,6,12],reli:[5,73],relu:[12,69,72],remark:[2,5],remind:[2,5],remov:32,renam:77,reorder:[12,62],reparametrize_scal:19,replac:[4,13,18,28,60,63,74],repo:[0,76],report:[3,12,48,49],repositori:[0,12,68,72,73,74,76,77],repres:[2,12,28,44,45,46,47,51,52,70,72],represent:[45,70,74],reproduc:[0,6,62,63,64],request:[12,41,73],requeue_zombie_tri:42,requir:[0,3,5,6,12,13,26,40,41,60,70,72,75,76,78],research:[73,74],reset:[19,20],reshap:[13,61],resiz:19,resize_snapshots_for_debug:19,resp:[5,12],respect:[3,10,12,20,70,72,73],respres:[46,51],restart:3,restrict:[11,12,60,64],restrict_data:64,restrict_target:12,resubmit:42,result:[3,6,12,18,19,33,51,55,64,70,71,72,74],result_typ:33,resultsfor:74,resum:[3,6,41,42],resume_checkpoint:[41,42],resumpt:[6,41,42],retain:[32,60],return_energy_contribut:63,return_outputs_directli:25,return_plot:[2,38],return_str:64,return_valu:[46,47],retval:60,reusabl:0,rev:[73,74],rewrit:26,rfname:60,right:[11,19,50,60],rmax:[12,64],robust:3,romero:[0,12],room:74,root:[0,22],rossendorf:74,roughli:73,rout:32,routin:[2,4,6,12,72],row:[12,22,46,51,72],rst:76,run:[0,3,5,11,12,25,32,36,41,42,53,54,56,63,69,72,76,77],run_exist:[3,6,54,56],run_nam:[36,54,56],runner:[7,37,53,55,56,67],runner_dict:54,runtim:4,ry:[2,58,62,63,70],s0:59,s1:59,s41524:73,s:[0,12,39,41,60,62,64,72,73,74,77],safe:1,sai:77,same:[3,6,12,18,19,20,23,32,38,42,50,59,60,63,64,69,77],samefileerror:75,sampl:[12,16,38,39,40,41,42,70,72],sampler:[12,41],sandia:74,save:[3,4,5,6,10,12,13,16,18,19,20,22,23,28,36,41,42,50,54,56,61,62,63,64,69,70,71,72],save_as_json:12,save_as_pickl:12,save_calcul:36,save_format:[12,22],save_nam:[4,6,23],save_network:50,save_path:[36,54],save_run:[54,72],save_runn:54,sbatch:6,scalabl:74,scalar:33,scale:[3,4,5,6,12,19,22,25,26,41,42,50,61,63,69,72,73,74,76],scaled_posit:61,scaler:22,scarc:18,scf:61,schedul:[6,12,42],scheme:[18,19,63],schmerler:[0,73,74],sci:74,scienc:73,scientif:[0,4,74],scikit:22,scontrol:6,score:[48,49],script:[3,5,6,11,12,69,77],se:36,search:[1,2,69],search_paramet:[48,49,52],second:12,secondli:[2,72],section:[6,68,69,70,71,72],see:[0,2,5,12,18,20,28,38,41,60,64,70,71,72,75,77],seed:[6,12],seem:[5,26],select:[2,6,12,13,55,70,72,77],self:[62,63],sell:[11,60],sendv:32,sens:[12,36,52,54,62,63,72],sep:[11,73],separ:[11,18,28,36,54,56,70,72,78],sequenc:50,seri:[4,13],serial:[10,11],serializ:10,serv:[50,53,74],server:42,servernam:3,set:[0,2,3,4,5,6,11,12,13,16,18,19,23,24,25,26,27,32,38,39,40,41,42,51,53,54,55,61,62,63,64,69,70,71,74,75],set_calcul:71,set_cmdlinevar:33,set_current_verbos:11,set_ddp_statu:11,set_lammps_inst:11,set_mpi_statu:11,set_optimal_paramet:[2,38,39,40,41,42,69],set_paramet:39,setup:[0,3,6,35,76],sever:[3,5,59,69,72],sgd:12,sh:77,shall:[11,60],sham:[73,74],shao:74,shape:[33,61,64],share:[26,27],shift:32,ship:75,shorter:6,should:[0,2,3,5,6,11,12,13,19,21,22,30,31,32,34,36,41,42,47,48,49,50,53,54,58,59,61,62,63,64,69,70,72,75,77],should_prun:[48,49],show:[0,6,12,74],show_order_of_import:41,showcas:[2,74],shown:[2,3,5,6,70,72],shuffl:[0,4,6,12,20,23,24,25,26],shuffle_snapshot:[4,6,23],shuffling_se:[6,12],shut:11,shutil:75,si:[13,32,61,62,63,64],si_dimens:[13,32,61,62,63,64],si_unit_convers:[13,32,61,62,63,64],sigma:[12,30,59],sigmoid:[12,69],sign:0,signal:72,signific:[12,74],significantli:[63,64],silver:73,similar:[2,3,16,74],simp:[59,61,62,63],simpl:[70,71,72],simplest:6,simpli:[5,6,12,16,19,36,51,61],simpson:[59,61,62,63],simul:[5,12,36,60,61,63,70,71,72,73,74,78],sinc:[2,3,5,6,12,18,30,31,32,34,36,42,71,72,76],singl:[3,5,6,18,24,26,33,55,68],site:13,siva:0,sivasankaran:[73,74],six:36,size:[0,3,5,11,12,13,26,39,43,44,45,46,47,50,52,69,72,74],skip:33,skiparraywrit:13,slice:[5,19],slightli:42,slow:6,slowest:12,slurm:6,slurm_job_nodelist:6,slurm_localid:6,slurm_nodelist:6,slurm_ntask:6,slurm_procid:6,small:[2,6,64,78],smaller:[12,25,69],smallest:[12,16],smear:62,smearing_factor:62,smith:64,smoothli:12,snap:[12,75],snapshot4:18,snapshot:[6,7,12,15,16,17,18,19,20,23,25,26,27,32,38,55,63,67,70,72],snapshot_correlation_cutoff:16,snapshot_directories_list:12,snapshot_funct:28,snapshot_numb:[19,55,63],snapshot_typ:[4,20,23,28],sneha:0,so:[2,3,4,6,11,12,22,50,54,60,61,62,70,72,74,75,76,77,78],societi:73,softwar:[0,5,11,60,70,71,73,74,78],sole:75,solv:59,somashekhar:0,some:[2,6,12,25,26,50,52,54,64,72],someth:[52,77],sometim:76,somewhat:12,soon:7,sort:[22,25,26,32,41],sourc:[0,9,10,11,12,13,15,16,18,19,20,22,23,24,25,26,27,28,30,31,32,33,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,58,59,60,61,62,63,64,65,71],space:[2,6,59,62,64,69,70,72,74,78],special:[2,24],specif:[3,4,6,12,19,39,50,59,64,71,76],specifi:[0,2,3,4,5,6,12,13,22,32,52,62,64,69,70,71,72],speed:[6,12,74],speedup:6,sphere:70,sphinxopt:76,split:[5,12],springer:41,sql:[3,42],sqlite:[3,12],sqlite_timeout:12,sqrt:59,squar:[6,12],src:75,srcname:60,srun:6,ssf:[12,64],ssf_paramet:12,stabl:12,standard:[3,4,5,12,22,69,72],start:[2,3,5,12,22,70],start_incremental_fit:22,starts_at:18,state:[12,50,62,63,71,74],statement:[5,11],static_structur:5,static_structure_factor_from_atom:[5,64],statu:11,stem:[62,63],step:[2,5,12,15,16,68,69,78],stephen:[0,73,74],steve:[0,73],still:[6,11,13,24,27,41,42,73,74],stochast:12,stop:[12,19,69,76],storag:[4,12,42],store:[1,3,12,25,26,36,61,64,70,72],str:[27,36,54,55,56,61,63],straightforward:[0,2,74],strategi:[3,69],strength:41,stress:36,stretch:5,string:[11,12,13,16,18,19,20,22,23,28,30,31,32,33,34,36,38,39,41,42,43,44,45,46,47,50,52,53,54,55,56,58,59,60,61,62,63,64,65],structur:[5,7,12,13,64,70,71,72,73,74,78],studi:[3,12,38,39,40,41,42,48,49,69,73],study_nam:[3,12,42],style:[0,51,64],sub:72,subclass:[43,50],subfold:12,subject:[11,60,76],sublicens:[11,60],submit:0,subobject:72,subroutin:63,subsequ:[12,53,74],subset:[39,40,42],substanti:[11,60],success:[75,77],successfulli:[75,76],suffic:32,suffici:0,suggest:[0,12,16,64],suit:[0,77],suitabl:[5,12,73,74,75,76],sum_i:62,sum_k:62,summari:64,summat:[61,63,64],supervis:0,supervisor:74,support:[0,3,4,5,6,12,20,28,36,39,41,43,44,45,46,47,52,55,58,59,61,62,63,64,75],suppos:[0,33,49,59,63],suppress:59,suppress_overflow:59,sure:[0,3,4,6,32,63,70,72,74,75,76,77],surrog:[12,48,49,74],switchflag:12,symbol:18,symmetri:[61,63],syntax:[2,3,6,72,76],system:[0,2,3,5,6,12,42,61,62,63,64,71,72,74,77],system_chang:36,t:[4,12,41,42,59,60,62,63,64,74,76],tag:[0,76],tahmasbi:0,take:[2,6,12,42,48,49,64],taken:[41,60],tamar:73,target:[2,6,7,11,12,16,18,19,20,23,25,26,27,28,30,31,34,36,38,48,49,50,53,58,61,62,63,67,70,71,72],target_calcul:[5,16,18,19,20,23,25,26,27,38,71],target_calculation_kwarg:70,target_calculator_kwarg:18,target_data:64,target_input_path:[18,38,70],target_input_typ:[18,38,70],target_save_path:[18,23,70],target_temperatur:16,target_typ:[12,70,72],target_unit:[2,18,38,70],targetbas:[58,62],task:[12,59,72,78],te:[20,28,55,72],te_mutex:61,team:[0,4,5,6,75,76],technic:[32,64],techniqu:[3,70,74],technol:74,technolog:73,tell:[3,72,75],tem:[12,64],temperatur:[5,6,12,16,36,53,59,62,63,64,72,73,74],tempor:16,ten:5,tend:64,tensor:[19,22,24,50,63],tensorboard:[0,12],tensordataset:[6,12,24],term:[50,62,63],termin:12,test:[0,4,6,12,19,20,21,25,28,48,49,53,55,69,70,76,77,78],test_al_debug_2k_nr:19,test_all_snapshot:[55,72],test_exampl:0,test_snapshot:55,tester:[6,7,19,37,53,54,56,67,72],text:4,than:[12,54,69],thei:[0,3,4,5,6,12,42,64,71],them:[0,6,23,32,62,70],themselv:[4,16,19],theorem:61,theori:[3,73,74],thereaft:[62,64],therefor:[4,25,26,32,61,78],therein:[12,73],thermodynam:59,thi:[0,1,2,3,4,5,6,10,11,12,13,15,16,18,19,20,22,23,24,25,26,27,28,30,31,32,33,34,36,38,39,40,41,42,46,48,49,50,51,52,53,54,55,56,58,59,60,61,62,63,64,68,69,70,71,72,73,74,75,76,77,78],thing:[69,70],third:72,thompson:[0,73,74],those:[12,72,77],though:[12,64],thousand:5,thread:11,three:[5,12,64,72,78],three_particle_correlation_function_from_atom:64,threshold:16,through:[3,11,50,61,72],throughout:55,thrown:11,thu:[0,6,12,19,76],time:[0,3,5,6,12,42,70,72,73,77],timeout:12,timestep:[12,16],timothi:0,titl:73,tmp:70,to_json:[10,12],togeth:[6,69],token:50,toml:[0,12],too:[2,32],tool:[4,14,15,16,64],topic:[70,71],torch:[6,18,19,22,24,25,26,50,63,76],torchrun:6,tort:[11,60],total:[0,5,12,55,61,62,63,64,71,72,74,78],total_energi:[12,55,63,71,77],total_energy_contribut:61,total_energy_ful:55,total_energy_modul:77,tpcf:[12,64],tpcf_paramet:12,tpe:41,tr:[4,20,28,55,72],track:19,train:[0,1,2,3,5,7,12,19,20,23,25,28,36,40,41,42,48,49,51,52,54,56,64,68,69,71,73,74,76,78],train_network:[56,72],trainer:[3,6,7,12,37,54,67,72],training_report_frequ:12,trainingtyp:[12,69,72],traj:15,trajectori:[12,15,16,64],trajectory_analysis_below_average_count:12,trajectory_analysis_correlation_metric_cutoff:12,trajectory_analysis_denoising_width:12,trajectory_analysis_estimated_equilibrium:12,trajectory_analysis_temperature_tolerance_perc:12,trajectory_analyz:[7,14,67],trajectoryanalyz:16,transfer:[0,6,73,74],transform:[12,19,22,25,50,61,64,70],transformernet:50,trapezoid:[59,61,62,63],trapz:[59,61,62,63],treat:[11,76],tree:[0,75],trex:11,trial:[3,12,39,40,41,42,46,47,48,49,51,69],trial_ensemble_evalu:12,trial_list:40,trial_typ:52,tricki:24,trivial:[2,5,6],truth:72,tune:[0,3,6,12,41,69,72],turn:6,tutori:[4,6,72],tweak:[68,71],twice:[5,64],two:[2,12,13,16,60,69,72,73],twojmax:12,txt:[0,62,76],type:[10,11,12,13,16,18,19,22,24,28,30,31,32,33,34,36,38,39,41,42,43,46,47,48,49,50,53,54,55,56,58,59,60,61,62,63,64,70],typestr:22,typic:75,u:[3,6],ubuntu:78,uncach:[16,61,62,63],uncache_properti:[16,61,62,63],uncertainti:0,unchang:[26,61],uncorrel:[12,16],under:[0,36,54,56],underlin:63,understand:74,uniform:[50,59],unit:[13,18,19,20,23,25,26,27,28,30,31,32,34,38,50,58,61,62,63,64],unless:61,unload:6,unnecessari:[19,54],unscal:22,unseen:72,untest:77,until:[12,25,26,69,70],untouch:4,up:[0,2,6,12,32,42,61,62,63,64,69,70,74],updat:0,upon:[0,3,12,19,42,45,50,70],upper:[5,69],upward:12,url:73,us:[0,1,2,3,4,7,11,12,13,15,16,18,19,20,22,23,24,25,26,27,30,31,32,33,34,36,38,39,40,41,42,43,44,45,46,47,48,49,50,52,53,54,55,56,58,59,60,61,62,63,64,68,69,70,72,73,74,75,76,77,78],usag:[0,5,6,19,54,63,68,71,72,74,75],use_ddp:[6,12,22,25,26],use_fast_tensor_data_set:[6,12],use_fp64:[18,33],use_gauss_ldo:70,use_gpu:[5,6,12],use_graph:[6,12],use_lammp:12,use_lazy_load:[6,12,72],use_lazy_loading_prefetch:[6,12],use_memmap:63,use_mixed_precis:[6,12],use_mpi:[2,3,5,12],use_multivari:12,use_pickled_comm:32,use_pkl_checkpoint:[38,39,40,41,42,56],use_shuffling_for_sampl:12,use_y_split:[5,12],use_z_split:12,useabl:70,used_data_handl:63,user:[4,11,12,16,48,49,59,63,72,76],userwarn:11,usual:[5,6,12,16,32,50,51,61,62,64,70],util:[6,24,25,26],v1:76,v2:12,v80:12,v:[74,75],v_:61,va:[20,28,55,72],vaidyanathan:60,valid:[3,6,12,19,20,28,69,72],validation_loss:12,validation_loss_old:12,valu:[2,5,6,11,12,13,16,25,26,30,32,40,41,46,47,48,49,50,52,53,55,59,60,61,62,63,64,69,70,72],valuabl:0,vari:77,variabl:[6,12,16,19,54,64],varianc:25,varieti:74,variou:[12,71,72,74],vector:[2,12,25,26,32,60,64,70,72],verbos:[11,12,62,70,72],veri:[0,3,6,12,50,62],verif:72,verifi:72,verma:0,versatil:74,version:[7,12,18,24,48,49,67,70,75,76,77],via:[0,2,3,5,6,11,12,16,21,26,61,62,63,64,69,70,71,72,75,76,77,78],viabl:48,view:[2,6,33],viewdoc:64,viewer:4,virtu:6,visibl:50,visit:[3,4],visual:[4,6,12,74],visualis:[6,12],visualisation_dir:[6,12],visualisation_dir_append_d:12,visualizatuon:6,vladyslav:[0,73],vogel:[0,73,74],volta:75,volum:73,volumetr:[4,60,65,70,72],voxel:[30,61,63],w:[41,63,76],w_k:62,wa:[5,6,22,25,26,38,39,40,41,42,50,54,56,61,62,63,64,71],wai:[0,3,6,12,64],wait:[12,42],wait_tim:[3,12],want:[2,5,6,20,23,39,43,44,45,46,47,64,69,72,75,76],warmli:0,warn:[3,11,76],warranti:[11,60],wave:[12,64],wavefunct:61,we:[0,2,3,5,12,22,25,26,32,36,64,65,69,70,72,73,75,77],websit:[3,76],weight:[6,12,50,59,72],weight_decai:12,welcom:0,well:[2,3,6,12,61,68,69,76],were:[5,72],what:[0,20,23,32,36,54,56,60,72],whatev:75,when:[0,1,3,4,6,11,12,18,19,20,28,32,42,48,49,50,54,56,60,63,64,69,70,72,77,78],whenev:72,where:[4,5,6,12,26,36,41,42,54,56,72,75],wherea:70,whether:[9,11,12,25,32,48,49,60],which:[0,2,3,4,5,6,9,12,13,15,16,18,19,20,21,22,23,28,30,31,32,33,34,36,38,39,40,41,42,46,47,48,49,50,51,53,54,55,56,58,59,60,61,62,63,64,69,70,71,72,75,76,77,78],whom:[11,60],wide:74,width:[12,30],window:[76,78],wip:63,wise:[6,12,22,69,72],wish:[5,77],within:[2,11,12,13,19,24,63,72],without:[0,3,6,11,12,13,40,52,59,60,64,75],won:[41,42],wonjoon:11,work:[0,3,5,6,11,12,33,40,55,60,61,62,63,64,69,77,78],worker:[6,12],workflow:[2,3,4,5,6,28,35,71,72,73,74],working_directori:[32,70],world:22,world_siz:6,worldwid:74,would:[2,13,61],wrap:0,write:[4,13,32,60,61,64],write_additional_calculation_data:64,write_cub:60,write_imcub:60,write_tem_input_fil:64,write_to_cub:[5,61],write_to_numpy_fil:[13,64],write_to_openpmd_fil:[13,61,64],write_to_openpmd_iter:13,written:[38,39,40,41,42,61,64],wuantiti:[61,62,63,64],x86_64:77,x:[5,12,19,32,50,59,64,70,74],xarg:0,xc:61,xcrysden:63,xsf:[61,63,65],xsf_parser:[7,57,67],xvec:60,xyz:[12,32],y:[5,12,19,32,64],yaml:0,ye:75,year:73,yet:[4,6,13,30,31,34,64],yield:[2,6],you:[0,2,3,4,5,6,12,20,23,39,43,44,45,46,47,50,68,70,71,72,73,74,75,76,77,78],your:[0,2,4,5,6,12,70,72,73,74,75,76,77],yourself:68,yovel:[73,74],ysplit:5,yt:4,yvec:60,z:[5,12,19,32,64,73,74],zentrum:74,zero:[5,12,50,69],zero_out_neg:12,zip:[36,54,56,72],zip_run:[54,56],zipextfil:[12,22,50],zombi:42,zone:59,zvec:60},titles:["Contributions","Advanced options","Improved data conversion","Improved hyperparameter optimization","Storing data with OpenPMD","Using MALA in production","Improved training performance","mala","common","check_modules","json_serializable","parallelizer","parameters","physical_data","datageneration","ofdft_initializer","trajectory_analyzer","datahandling","data_converter","data_handler","data_handler_base","data_repo","data_scaler","data_shuffler","fast_tensor_dataset","lazy_load_dataset","lazy_load_dataset_single","multi_lazy_load_data_loader","snapshot","descriptors","atomic_density","bispectrum","descriptor","lammps_utils","minterpy_descriptors","interfaces","ase_calculator","network","acsd_analyzer","hyper_opt","hyper_opt_naswot","hyper_opt_oat","hyper_opt_optuna","hyperparameter","hyperparameter_acsd","hyperparameter_naswot","hyperparameter_oat","hyperparameter_optuna","multi_training_pruner","naswot_pruner","network","objective_base","objective_naswot","predictor","runner","tester","trainer","targets","atomic_force","calculation_helpers","cube_parser","density","dos","ldos","target","xsf_parser","version","API reference","Getting started with MALA","Basic hyperparameter optimization","Data generation and conversion","Using ML-DFT models for predictions","Training an ML-DFT model","Citing MALA","Welcome to MALA!","Installing LAMMPS","Installing MALA","Installing Quantum ESPRESSO (total energy module)","Installation"],titleterms:{"do":62,"public":74,ASE:71,acsd_analyz:38,ad:[0,72,76],advanc:[1,3,6],algorithm:3,an:72,api:67,ase_calcul:36,atomic_dens:30,atomic_forc:58,basic:69,behind:74,bispectrum:31,branch:0,build:[72,75,76,77],calcul:71,calculation_help:59,check_modul:9,checkpoint:[3,6],cite:73,code:0,common:8,content:74,contribut:0,contributor:0,convers:[2,70],cpu:5,creat:0,cube_pars:60,data:[2,4,70,72,76],data_convert:18,data_handl:19,data_handler_bas:20,data_repo:21,data_scal:22,data_shuffl:23,datagener:14,datahandl:17,densiti:61,depend:0,descriptor:[2,29,32],develop:0,dft:[71,72],document:76,doe:74,download:76,energi:77,espresso:77,exampl:76,extens:[75,77],fast_tensor_dataset:24,format:0,gener:70,get:68,gpu:[5,6],how:74,hyper_opt:39,hyper_opt_naswot:40,hyper_opt_oat:41,hyper_opt_optuna:42,hyperparamet:[3,43,69],hyperparameter_acsd:44,hyperparameter_naswot:45,hyperparameter_oat:46,hyperparameter_optuna:47,improv:[2,3,6],instal:[75,76,77,78],interfac:35,issu:0,json_serializ:10,lammp:75,lammps_util:33,lazi:6,lazy_load_dataset:25,lazy_load_dataset_singl:26,ldo:63,librari:76,licens:0,list:69,load:6,local:76,mala:[0,5,7,68,71,73,74,76],metric:6,minterpy_descriptor:34,ml:[71,72],model:[71,72],modul:77,multi_lazy_load_data_load:27,multi_training_prun:48,naswot_prun:49,network:[37,50],objective_bas:51,objective_naswot:52,observ:5,ofdft_initi:15,openpmd:4,optim:[3,69],option:[1,76],parallel:[2,3,5,6,11],paramet:[12,72],perform:6,physical_data:13,predict:[5,71],predictor:53,prerequisit:[75,76,77],product:5,pull:0,python:[75,76,77],quantum:77,recommend:76,refer:67,releas:0,request:0,run:6,runner:54,search:3,set:72,snapshot:28,start:[68,74],store:4,strategi:0,target:[57,64],tensorboard:6,test:72,tester:55,total:77,train:[6,72],trainer:56,trajectory_analyz:16,tune:2,us:[5,6,71],version:[0,66],visual:5,welcom:74,what:74,where:74,who:74,work:74,xsf_parser:65}})
\ No newline at end of file