refactor: format code using black, use max_epochs instead of epochs

configs/_base_/default_runtime_cls.py

@@ -5,19 +5,14 @@
 default_hooks = dict(
  # record the time of every iteration.
  timer=dict(type='IterTimerHook'),
-
  # print log every 100 iterations.
  logger=dict(type='TextLoggerHook', interval=100),
-
  # enable the parameter scheduler.
  param_scheduler=dict(type='ParamSchedulerHook'),
-
  # save checkpoint per epoch.
  checkpoint=dict(type='CheckpointHook', save_best='auto', interval=1),
-
  # set sampler seed in distributed evrionment.
  sampler_seed=dict(type='DistSamplerSeedHook'),
-
  # validation results visualization, set True to enable it.
  visualization=dict(type='mmcls.VisualizationHook', enable=False),
 )
@@ -26,10 +21,8 @@
 env_cfg = dict(
  # whether to enable cudnn benchmark
  cudnn_benchmark=False,
-
  # set multi process parameters
  mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
-
  # set distributed parameters
  dist_cfg=dict(backend='nccl'),
 )

configs/_base_/default_runtime_det.py

@@ -6,8 +6,8 @@
  param_scheduler=dict(type='ParamSchedulerHook'),
  checkpoint=dict(type='CheckpointHook', interval=1),
  sampler_seed=dict(type='DistSamplerSeedHook'),
- visualization=dict(type='mmdet.DetVisualizationHook')
- )
+ visualization=dict(type='mmdet.DetVisualizationHook'),
+)
 
 env_cfg = dict(
  cudnn_benchmark=False,
@@ -16,11 +16,12 @@
 )
 
 
-vis_backends = [dict(type='LocalVisBackend'),
- # dict(type='WandbVisBackend'),
- dict(type='TensorboardVisBackend')]
-visualizer = dict(
- type='edgelab.FomoLocalVisualizer', vis_backends=vis_backends, name='visualizer')
+vis_backends = [
+ dict(type='LocalVisBackend'),
+ # dict(type='WandbVisBackend'),
+ dict(type='TensorboardVisBackend'),
+]
+visualizer = dict(type='edgelab.FomoLocalVisualizer', vis_backends=vis_backends, name='visualizer')
 
 
 log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
@@ -29,7 +30,6 @@
 load_from = None
 resume = False
 
-train_cfg = dict(by_epoch=True,max_epochs=300)
+train_cfg = dict(by_epoch=True, max_epochs=300)
 val_cfg = dict()
 test_cfg = dict()
-

configs/_base_/default_runtime_pose.py

@@ -30,12 +30,10 @@
  # dict(type='TensorboardVisBackend'),
  # dict(type='WandbVisBackend'),
 ]
-visualizer = dict(
- type='mmpose.PoseLocalVisualizer',radius=1, vis_backends=vis_backends, name='visualizer')
+visualizer = dict(type='mmpose.PoseLocalVisualizer', radius=1, vis_backends=vis_backends, name='visualizer')
 
 # logger
-log_processor = dict(
- type='LogProcessor', window_size=50, by_epoch=True, num_digits=6)
+log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True, num_digits=6)
 log_level = 'INFO'
 load_from = None
 resume = False
@@ -44,6 +42,6 @@
 backend_args = dict(backend='local')
 
 # training/validation/testing progress
-train_cfg = dict(by_epoch=True,max_epochs=210,val_interval=5)
+train_cfg = dict(by_epoch=True, max_epochs=210, val_interval=5)
 val_cfg = dict()
 test_cfg = dict()

configs/_base_/schedules/schedule_1x.py

@@ -5,21 +5,12 @@
 
 # learning rate
 param_scheduler = [
- dict(
- type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
- dict(
- type='MultiStepLR',
- begin=0,
- end=12,
- by_epoch=True,
- milestones=[8, 11],
- gamma=0.1)
+ dict(type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
+ dict(type='MultiStepLR', begin=0, end=12, by_epoch=True, milestones=[8, 11], gamma=0.1),
 ]
 
 # optimizer
-optim_wrapper = dict(
- type='OptimWrapper',
- optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
+optim_wrapper = dict(type='OptimWrapper', optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
 
 # Default setting for scaling LR automatically
 # - `enable` means enable scaling LR automatically

configs/_base_/schedules/schedule_20e.py

@@ -5,21 +5,12 @@
 
 # learning rate
 param_scheduler = [
- dict(
- type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
- dict(
- type='MultiStepLR',
- begin=0,
- end=20,
- by_epoch=True,
- milestones=[16, 19],
- gamma=0.1)
+ dict(type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
+ dict(type='MultiStepLR', begin=0, end=20, by_epoch=True, milestones=[16, 19], gamma=0.1),
 ]
 
 # optimizer
-optim_wrapper = dict(
- type='OptimWrapper',
- optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
+optim_wrapper = dict(type='OptimWrapper', optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
 
 # Default setting for scaling LR automatically
 # - `enable` means enable scaling LR automatically

configs/_base_/schedules/schedule_2x.py

@@ -5,21 +5,12 @@
 
 # learning rate
 param_scheduler = [
- dict(
- type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
- dict(
- type='MultiStepLR',
- begin=0,
- end=24,
- by_epoch=True,
- milestones=[16, 22],
- gamma=0.1)
+ dict(type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
+ dict(type='MultiStepLR', begin=0, end=24, by_epoch=True, milestones=[16, 22], gamma=0.1),
 ]
 
 # optimizer
-optim_wrapper = dict(
- type='OptimWrapper',
- optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
+optim_wrapper = dict(type='OptimWrapper', optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
 
 # Default setting for scaling LR automatically
 # - `enable` means enable scaling LR automatically

configs/accelerometer/3axes_accelerometer_62.5Hz_1s_classify.py

@@ -5,36 +5,42 @@
 num_classes = 3
 num_axes = 3
 frequency = 62.5
-window=1000
-
-model = dict(type='AccelerometerClassifier',
- backbone=dict(type='AxesNet',
- num_axes=num_axes,
- frequency=frequency,
- window=window,
- num_classes=num_classes,
- ),
- head=dict(type='edgelab.ClsHead',
- loss=dict(type='mmcls.CrossEntropyLoss', loss_weight=1.0),
- topk=(1, 5),
- ))
+window = 1000
+
+model = dict(
+ type='AccelerometerClassifier',
+ backbone=dict(
+ type='AxesNet',
+ num_axes=num_axes,
+ frequency=frequency,
+ window=window,
+ num_classes=num_classes,
+ ),
+ head=dict(
+ type='edgelab.ClsHead',
+ loss=dict(type='mmcls.CrossEntropyLoss', loss_weight=1.0),
+ topk=(1, 5),
+ ),
+)
 
 # dataset settings
 dataset_type = 'edgelab.SensorDataset'
 data_root = './datasets/aixs-export'
 batch_size = 1
 workers = 1
 
-shape = (num_classes * int(62.5 * 1000 / 1000))
+shape = num_classes * int(62.5 * 1000 / 1000)
 
-train_pipeline = [ dict(type='edgelab.LoadSensorFromFile'),
- dict(type='edgelab.PackSensorInputs'),
+train_pipeline = [
+ dict(type='edgelab.LoadSensorFromFile'),
+ dict(type='edgelab.PackSensorInputs'),
 ]
 
-test_pipeline = [ dict(type='edgelab.LoadSensorFromFile'),
- dict(type='edgelab.PackSensorInputs'),
+test_pipeline = [
+ dict(type='edgelab.LoadSensorFromFile'),
+ dict(type='edgelab.PackSensorInputs'),
 ]
- 
+
 train_dataloader = dict(
  batch_size=batch_size,
  num_workers=workers,
@@ -72,18 +78,16 @@
 
 # optimizer
 lr = 0.0005
-epochs = 10
+max_epochs = 10
 
-optim_wrapper = dict(
- type='OptimWrapper',
- optimizer=dict(type='Adam', lr=lr, betas=[0.9, 0.99], weight_decay=0))
+optim_wrapper = dict(type='OptimWrapper', optimizer=dict(type='Adam', lr=lr, betas=[0.9, 0.99], weight_decay=0))
 
 
-train_cfg = dict(by_epoch=True, max_epochs=epochs)
+train_cfg = dict(by_epoch=True, max_epochs=max_epochs)
 
 val_cfg = dict()
 test_cfg = dict()
 
 # set visualizer
 vis_backends = [dict(type='LocalVisBackend')]
-visualizer = dict(type='edgelab.SensorClsVisualizer', vis_backends=vis_backends, name='visualizer')
+visualizer = dict(type='edgelab.SensorClsVisualizer', vis_backends=vis_backends, name='visualizer')