Merge branch 'develop'

amaiya · Aug 2, 2019 · 21ac7a5 · 21ac7a5
2 parents 285ed3b + 17f54f5
commit 21ac7a5
Show file tree

Hide file tree

Showing 15 changed files with 737 additions and 28 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -6,6 +6,21 @@ Most recent releases are shown at the top. Each release shows:
 - **Changed**: Additional parameters, changes to inputs or outputs, etc
 - **Fixed**: Bug fixes that don't change documented behaviour
 
+## 0.1.10 (2019-08-02)
+
+### New:
+- N/A
+
+### Changed:
+- For ```Learner.lr_find```, removed epochs and max_lr arguments and added lr_mult argument
+  Default lr_mult is 1.01, but can be changed to control size of sample being used
+  to estimate learning rate.
+- Changed structure of examples folder
+
+### Fixed:
+- Resolved issue with ```utils.y_from_data``` not working correctly with DataFrameIterator objects.
+
+
 ## 0.1.9 (2019-08-01)
 
 ### New:

diff --git a/examples/text/IMDb-fasttext.ipynb b/examples/text/IMDb-fasttext.ipynb
diff --git a/examples/toxic_comments-bigru.ipynb → examples/text/toxic_comments-bigru.ipynb b/examples/toxic_comments-bigru.ipynb → examples/text/toxic_comments-bigru.ipynb
diff --git a/examples/text/toxic_comments-fasttext.ipynb b/examples/text/toxic_comments-fasttext.ipynb
diff --git a/examples/cifar10-WRN22.ipynb → examples/vision/cifar10-WRN22.ipynb b/examples/cifar10-WRN22.ipynb → examples/vision/cifar10-WRN22.ipynb
@@ -327,7 +327,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.6.8"
   }
  },
  "nbformat": 4,

diff --git a/examples/dogs_vs_cats-ResNet50.ipynb → examples/vision/dogs_vs_cats-ResNet50.ipynb b/examples/dogs_vs_cats-ResNet50.ipynb → examples/vision/dogs_vs_cats-ResNet50.ipynb
@@ -21,7 +21,6 @@
     "os.environ[\"CUDA_DEVICE_ORDER\"]=\"PCI_BUS_ID\";\n",
     "os.environ[\"CUDA_VISIBLE_DEVICES\"]=\"0\" \n",
     "import sys\n",
-    "sys.path.append('..')\n",
     "import ktrain\n",
     "from ktrain import vision as vis"
    ]
@@ -53,7 +52,7 @@
     }
    ],
    "source": [
-    "DATADIR = '../data/dogscats'\n",
+    "DATADIR = 'data/dogscats'\n",
     "(train_data, val_data, preproc) = vis.images_from_folder(\n",
     "                                              datadir=DATADIR,\n",
     "                                              data_aug = vis.get_data_aug(horizontal_flip=True),\n",
@@ -238,7 +237,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.6.8"
   }
  },
  "nbformat": 4,

diff --git a/examples/mnist-WRN22.ipynb → examples/vision/mnist-WRN22.ipynb b/examples/mnist-WRN22.ipynb → examples/vision/mnist-WRN22.ipynb
@@ -367,7 +367,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.6.8"
   }
  },
  "nbformat": 4,

diff --git a/examples/pets-ResNet50.ipynb → examples/vision/pets-ResNet50.ipynb b/examples/pets-ResNet50.ipynb → examples/vision/pets-ResNet50.ipynb
@@ -683,7 +683,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.6.8"
   }
  },
  "nbformat": 4,

diff --git a/examples/vision/planet-ResNet50.ipynb b/examples/vision/planet-ResNet50.ipynb
diff --git a/ktrain/core.py b/ktrain/core.py
@@ -416,7 +416,7 @@ def reset_weights(self, nosave=False, verbose=1):
 
 
 
-    def lr_find(self, start_lr=1e-7, epochs=5, verbose=1):
+    def lr_find(self, start_lr=1e-7, lr_mult=1.01, verbose=1):
         """
         Plots loss as learning rate is increased.
         Highest learning rate corresponding to a still
@@ -425,8 +425,7 @@ def lr_find(self, start_lr=1e-7, epochs=5, verbose=1):
         Reference: https://arxiv.org/abs/1506.01186
 
         Args:
-            epochs (int): maximum number of epochs to simulate training
-                          If None, chosen automatically.
+            lr_mult (float): multiplication factor to increase LR.
             start_lr (float): smallest lr to start simulation
             verbose (bool): specifies how much output to print
         Returns:
@@ -446,8 +445,7 @@ def lr_find(self, start_lr=1e-7, epochs=5, verbose=1):
         try:
             # track and plot learning rates
             self.lr_finder = LRFinder(self.model)
-            self.lr_finder.find(self.train_data, start_lr=start_lr, end_lr=10, 
-                                epochs=epochs,
+            self.lr_finder.find(self.train_data, start_lr=start_lr, lr_mult=lr_mult, 
                                 workers=self.workers, 
                                 use_multiprocessing=self.use_multiprocessing, 
                                 verbose=verbose)

diff --git a/ktrain/lroptimize/lrfinder.py b/ktrain/lroptimize/lrfinder.py
@@ -53,7 +53,7 @@ def on_batch_end(self, batch, logs):
         K.set_value(self.model.optimizer.lr, lr)
 
 
-    def find(self, train_data, start_lr, end_lr, epochs=None, batch_size=U.DEFAULT_BS,
+    def find(self, train_data, start_lr, lr_mult=1.01, batch_size=U.DEFAULT_BS,
              workers=1, use_multiprocessing=False, verbose=1):
         """
         Track loss as learning rate is increased.
@@ -76,12 +76,8 @@ def find(self, train_data, start_lr, end_lr, epochs=None, batch_size=U.DEFAULT_B
             use_gen = False
             steps_per_epoch = np.ceil(num_samples/batch_size)
 
-        if epochs is None:
-            epochs = math.ceil(SAMPLE_SIZE/steps_per_epoch)
-
-
-        num_batches = epochs * steps_per_epoch
-        self.lr_mult = (end_lr / start_lr) ** (1 / num_batches)
+        epochs = 1024
+        self.lr_mult = lr_mult
 
         # Save weights into a file
         new_file, self._weightfile = tempfile.mkstemp()

diff --git a/ktrain/utils.py b/ktrain/utils.py
@@ -100,12 +100,12 @@ def nclasses_from_data(data):
 
 def y_from_data(data):
     if is_iter(data):
-        if hasattr(data, 'classes'):
+        if hasattr(data, 'classes'): # DirectoryIterator
             return to_categorical(data.classes)
-        elif hasattr(data, 'data'):
-            return data.data
-        elif hasattr(data, 'y'):
-            return data.y
+        elif hasattr(data, 'labels'):  # DataFrameIterator
+            return data.labels
+        elif hasattr(data, 'y'): # NumpyArrayIterator
+            return to_categorical(data.y)
         else:
             raise Exception('could not determine number of classes from %s' % (type(data)))
     else:

diff --git a/ktrain/version.py b/ktrain/version.py
@@ -1,2 +1,2 @@
 __all__ = ['__version__']
-__version__ = '0.1.9'
+__version__ = '0.1.10'
diff --git a/tutorial-03-image-classification.ipynb b/tutorial-03-image-classification.ipynb
@@ -1208,7 +1208,7 @@
    "outputs": [],
    "source": [
     "y_pred = learner.model.predict_generator(val_data)\n",
-    "y_true = val_data._data"
+    "y_true = val_data.labels"
    ]
   },
   {
@@ -1544,7 +1544,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.6.8"
   }
  },
  "nbformat": 4,

diff --git a/tutorial-04-text-classification.ipynb b/tutorial-04-text-classification.ipynb
@@ -569,7 +569,7 @@
    "source": [
     "Finally, we will train our model for 8 epochs using ```autofit``` with a learning rate of 0.0007. Having explicitly specified the number of epochs, ```autofit``` will automatically employ a triangular learning rate policy. Our final ROC-AUC score is **0.98**.\n",
     "\n",
-    "As shown in [this example notebook](https://github.com/amaiya/ktrain/blob/master/examples/toxic_comments-bigru.ipynb) on our GitHub project, even better results can be obtained using a Bidirectional GRU with pretrained word vectors (called ‘bigru’ in ktrain)"
+    "As shown in [this example notebook](https://github.com/amaiya/ktrain/blob/master/examples/text/toxic_comments-bigru.ipynb) on our GitHub project, even better results can be obtained using a Bidirectional GRU with pretrained word vectors (called ‘bigru’ in ktrain)"
    ]
   },
   {
@@ -785,7 +785,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.6.8"
   }
  },
  "nbformat": 4,