update tsn rgb models

configs/recognition/tsn/README.md

@@ -16,6 +16,8 @@
 |[tsn_r50_1x1x5_50e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x5_50e_kinetics400_rgb.py) | ResNet50 |68.64|88.19| x | x | [ckpt]() | [log]()|
 |[tsn_r50_dense_1x1x5_50e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x5_50e_kinetics400_rgb.py) | ResNet50 |68.59|88.31| x | x | [ckpt]() | [log]()|
 |[tsn_r50_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x8_100e_kinetics400_rgb.py) | ResNet50 |69.41|88.37| x | x | [ckpt]() | [log]()|
+|[tsn_r50_shortedge_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_shortedge_1x1x3_100e_kinetics400_rgb.py) | ResNet50 |70.91|89.51| x | x | [ckpt]() | [log]() |
+|[tsn_r50_shortedge_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_shortedge_1x1x8_100e_kinetics400_rgb.py) | ResNet50 |72.41|90.55| x | x | [ckpt]() | [log]() |
 |[tsn_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x8_100e_kinetics400_rgb.py) | ResNet50 |70.77|89.3| x | x | [ckpt]() | [log]()|
 |[tsn_r50_video_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_video_1x1x3_100e_kinetics400_rgb.py) | ResNet50 | x | x | x | x | [ckpt]() | [log]()|
 

configs/recognition/tsn/tsn_r50_shortedge_1x1x3_100e_kinetics400_rgb.py

+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='ResNet',
+        pretrained='torchvision://resnet50',
+        depth=50,
+        norm_eval=False),
+    cls_head=dict(
+        type='TSNHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.4,
+        init_std=0.01))
+# model training and testing settings
+train_cfg = None
+test_cfg = dict(average_clips=None)
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = 'data/kinetics400/rawframes_train_shortedge/'
+data_root_val = 'data/kinetics400/rawframes_val_shortedge/'
+ann_file_train = 'data/kinetics400/kinetics_train_list_shortedge.txt'
+ann_file_val = 'data/kinetics400/kinetics_val_list_shortedge.txt'
+ann_file_test = 'data/kinetics400/kinetics_val_list_shortedge.txt'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
+mc_cfg = dict(
+    server_list_cfg='/mnt/lustre/share/memcached_client/server_list.conf',
+    client_cfg='/mnt/lustre/share/memcached_client/client.conf',
+    sys_path='/mnt/lustre/share/pymc/py3')
+train_pipeline = [
+    dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=3),
+    dict(type='FrameSelector', io_backend='memcached', **mc_cfg),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='RandomResizedCrop'),
+    dict(type='Resize', scale=(224, 224), keep_ratio=False),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs', 'label'])
+]
+val_pipeline = [
+    dict(
+        type='SampleFrames',
+        clip_len=1,
+        frame_interval=1,
+        num_clips=3,
+        test_mode=True),
+    dict(type='FrameSelector', io_backend='memcached', **mc_cfg),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='CenterCrop', crop_size=256),
+    dict(type='Flip', flip_ratio=0),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+test_pipeline = [
+    dict(
+        type='SampleFrames',
+        clip_len=1,
+        frame_interval=1,
+        num_clips=25,
+        test_mode=True),
+    dict(type='FrameSelector', io_backend='memcached', **mc_cfg),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='ThreeCrop', crop_size=256),
+    dict(type='Flip', flip_ratio=0),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+data = dict(
+    videos_per_gpu=32,
+    workers_per_gpu=4,
+    train=dict(
+        type=dataset_type,
+        ann_file=ann_file_train,
+        data_prefix=data_root,
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        data_prefix=data_root_val,
+        pipeline=val_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=ann_file_test,
+        data_prefix=data_root_val,
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
+# learning policy
+lr_config = dict(policy='step', step=[40, 80])
+total_epochs = 100
+checkpoint_config = dict(interval=5)
+evaluation = dict(
+    interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'], topk=(1, 5))
+log_config = dict(
+    interval=20,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook'),
+    ])
+# runtime settings
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/tsn_r50_shortedge_1x1x3_100e_kinetics400_rgb/'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]

configs/recognition/tsn/tsn_r50_shortedge_1x1x8_100e_kinetics400_rgb.py

+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='ResNet',
+        pretrained='torchvision://resnet50',
+        depth=50,
+        norm_eval=False),
+    cls_head=dict(
+        type='TSNHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.4,
+        init_std=0.01))
+# model training and testing settings
+train_cfg = None
+test_cfg = dict(average_clips=None)
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = 'data/kinetics400/rawframes_train_shortedge/'
+data_root_val = 'data/kinetics400/rawframes_val_shortedge/'
+ann_file_train = 'data/kinetics400/kinetics_train_list_shortedge.txt'
+ann_file_val = 'data/kinetics400/kinetics_val_list_shortedge.txt'
+ann_file_test = 'data/kinetics400/kinetics_val_list_shortedge.txt'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
+mc_cfg = dict(
+    server_list_cfg='/mnt/lustre/share/memcached_client/server_list.conf',
+    client_cfg='/mnt/lustre/share/memcached_client/client.conf',
+    sys_path='/mnt/lustre/share/pymc/py3')
+train_pipeline = [
+    dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8),
+    dict(type='FrameSelector', io_backend='memcached', **mc_cfg),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='RandomResizedCrop'),
+    dict(type='Resize', scale=(224, 224), keep_ratio=False),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs', 'label'])
+]
+val_pipeline = [
+    dict(
+        type='SampleFrames',
+        clip_len=1,
+        frame_interval=1,
+        num_clips=8,
+        test_mode=True),
+    dict(type='FrameSelector', io_backend='memcached', **mc_cfg),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='CenterCrop', crop_size=256),
+    dict(type='Flip', flip_ratio=0),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+test_pipeline = [
+    dict(
+        type='SampleFrames',
+        clip_len=1,
+        frame_interval=1,
+        num_clips=25,
+        test_mode=True),
+    dict(type='FrameSelector', io_backend='memcached', **mc_cfg),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='ThreeCrop', crop_size=256),
+    dict(type='Flip', flip_ratio=0),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+data = dict(
+    videos_per_gpu=12,
+    workers_per_gpu=4,
+    train=dict(
+        type=dataset_type,
+        ann_file=ann_file_train,
+        data_prefix=data_root,
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        data_prefix=data_root_val,
+        pipeline=val_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=ann_file_test,
+        data_prefix=data_root_val,
+        pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.00375, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
+# learning policy
+lr_config = dict(policy='step', step=[40, 80])
+total_epochs = 100
+checkpoint_config = dict(interval=1)
+evaluation = dict(
+    interval=2, metrics=['top_k_accuracy', 'mean_class_accuracy'], topk=(1, 5))
+log_config = dict(
+    interval=20,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook'),
+    ])
+# runtime settings
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/tsn_r50_shortedge_1x1x8_100e_kinetics400_rgb/'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]