Update big models

configs/recognition/slowfast/README.md

@@ -25,6 +25,9 @@
 |[slowfast_r50_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py) |short-side 320|8x3| ResNet50|None |75.64|92.3|1.6 ((32+4)x10x3 frames)|6203|[ckpt](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/slowfast_r50_4x16x1_256e_kinetics400_rgb_20200704-bcde7ed7.pth)| [log](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/20200704_232901.log)| [json](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/20200704_232901.log.json)|
 |[slowfast_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py) |short-side 256|8x4| ResNet50 |None |75.61|92.34|x|9062|[ckpt](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_256p_8x8x1_256e_kinetics400_rgb/slowfast_r50_256p_8x8x1_256e_kinetics400_rgb_20200810-863812c2.pth)|[log](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_256p_8x8x1_256e_kinetics400_rgb/20200731_151537.log)|[json](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_256p_8x8x1_256e_kinetics400_rgb/20200731_151537.log.json)|
 |[slowfast_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py) |short-side 320|8x3| ResNet50 |None|76.94|92.8|1.3 ((32+8)x10x3 frames)|9062| [ckpt](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/slowfast_r50_8x8x1_256e_kinetics400_rgb_20200716-73547d2b.pth) | [log](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/20200716_192653.log)| [json](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/20200716_192653.log.json)|
+|[slowfast_r101_r50_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r101_r50_4x16x1_256e_kinetics400_rgb.py) |short-side 256|8x1| ResNet101 + ResNet50 |None|76.69|93.07||16628| [ckpt](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r101_4x16x1_256e_kinetics400_rgb/slowfast_r101_4x16x1_256e_kinetics400_rgb_20210218-d8b58813.pth) | [log](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r101_4x16x1_256e_kinetics400_rgb/20210118_133528.log)| [json](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r101_4x16x1_256e_kinetics400_rgb/20210118_133528.log.json)|
+|[slowfast_r101_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r101_8x8x1_256e_kinetics400_rgb.py) |short-side 256|8x4| ResNet101 |None|77.90|93.51||25994| [ckpt](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r101_8x8x1_256e_kinetics400_rgb/slowfast_r101_8x8x1_256e_kinetics400_rgb_20210218-0dd54025.pth) | [log](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r101_8x8x1_256e_kinetics400_rgb/20210218_121513.log)| [json](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r101_8x8x1_256e_kinetics400_rgb/20210218_121513.log.json)|
+|[slowfast_r152_r50_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r152_r50_4x16x1_256e_kinetics400_rgb.py) |short-side 256|8x1| ResNet152 + ResNet50 |None|77.13|93.20||10077| [ckpt](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r152_4x16x1_256e_kinetics400_rgb/slowfast_r152_4x16x1_256e_kinetics400_rgb_20210122-bdeb6b87.pth) | [log](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r152_4x16x1_256e_kinetics400_rgb/20210122_131321.log)| [json](https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r152_4x16x1_256e_kinetics400_rgb/20210122_131321.log.json)|
 
 Notes:
 

configs/recognition/slowfast/slowfast_r101_8x8x1_256e_kinetics400_rgb.py

@@ -0,0 +1,137 @@
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet3dSlowFast',
+        pretrained=None,
+        resample_rate=4,  # tau
+        speed_ratio=4,  # alpha
+        channel_ratio=8,  # beta_inv
+        slow_pathway=dict(
+            type='resnet3d',
+            depth=101,
+            pretrained=None,
+            lateral=True,
+            fusion_kernel=7,
+            conv1_kernel=(1, 7, 7),
+            dilations=(1, 1, 1, 1),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            inflate=(0, 0, 1, 1),
+            norm_eval=False),
+        fast_pathway=dict(
+            type='resnet3d',
+            depth=101,
+            pretrained=None,
+            lateral=False,
+            base_channels=8,
+            conv1_kernel=(5, 7, 7),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            norm_eval=False)),
+    cls_head=dict(
+        type='SlowFastHead',
+        in_channels=2304,  # 2048+256
+        num_classes=400,
+        spatial_type='avg',
+        dropout_ratio=0.5))
+train_cfg = None
+test_cfg = dict(average_clips='prob')
+dataset_type = 'RawframeDataset'
+data_root = 'data/kinetics400/rawframes_train'
+data_root_val = 'data/kinetics400/rawframes_val'
+ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
+ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
+ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
+train_pipeline = [
+    dict(type='SampleFrames', clip_len=32, frame_interval=2, num_clips=1),
+    dict(type='RawFrameDecode'),
+    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='NCTHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs', 'label'])
+]
+val_pipeline = [
+    dict(
+        type='SampleFrames',
+        clip_len=32,
+        frame_interval=2,
+        num_clips=1,
+        test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='Flip', flip_ratio=0),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+test_pipeline = [
+    dict(
+        type='SampleFrames',
+        clip_len=32,
+        frame_interval=2,
+        num_clips=10,
+        test_mode=True),
+    dict(type='RawFrameDecode'),
+    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='NCTHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+data = dict(
+    videos_per_gpu=8,
+    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=0.1, momentum=0.9,
+    weight_decay=0.0001)  # this lr is used for 8 gpus
+optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='CosineAnnealing',
+    min_lr=0,
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=34)
+total_epochs = 256
+checkpoint_config = dict(interval=4)
+workflow = [('train', 1)]
+evaluation = dict(
+    interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
+log_config = dict(
+    interval=20,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        #    dict(type='TensorboardLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/slowfast_r101_8x8x1_256e_kinetics400_rgb'
+load_from = None
+resume_from = None
+find_unused_parameters = False

configs/recognition/slowfast/slowfast_r101_r50_4x16x1_256e_kinetics400_rgb.py

@@ -0,0 +1,136 @@
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet3dSlowFast',
+        pretrained=None,
+        resample_rate=8,  # tau
+        speed_ratio=8,  # alpha
+        channel_ratio=8,  # beta_inv
+        slow_pathway=dict(
+            type='resnet3d',
+            depth=101,
+            pretrained=None,
+            lateral=True,
+            conv1_kernel=(1, 7, 7),
+            dilations=(1, 1, 1, 1),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            inflate=(0, 0, 1, 1),
+            norm_eval=False),
+        fast_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=False,
+            base_channels=8,
+            conv1_kernel=(5, 7, 7),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            norm_eval=False)),
+    cls_head=dict(
+        type='SlowFastHead',
+        in_channels=2304,  # 2048+256
+        num_classes=400,
+        spatial_type='avg',
+        dropout_ratio=0.5))
+train_cfg = None
+test_cfg = dict(average_clips='prob')
+dataset_type = 'RawframeDataset'
+data_root = 'data/kinetics400/rawframes_train'
+data_root_val = 'data/kinetics400/rawframes_val'
+ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
+ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
+ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
+train_pipeline = [
+    dict(type='SampleFrames', clip_len=32, frame_interval=2, num_clips=1),
+    dict(type='RawFrameDecode'),
+    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='NCTHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs', 'label'])
+]
+val_pipeline = [
+    dict(
+        type='SampleFrames',
+        clip_len=32,
+        frame_interval=2,
+        num_clips=1,
+        test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='Flip', flip_ratio=0),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+test_pipeline = [
+    dict(
+        type='SampleFrames',
+        clip_len=32,
+        frame_interval=2,
+        num_clips=10,
+        test_mode=True),
+    dict(type='RawFrameDecode'),
+    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='NCTHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+data = dict(
+    videos_per_gpu=8,
+    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=0.1, momentum=0.9,
+    weight_decay=0.0001)  # this lr is used for 8 gpus
+optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='CosineAnnealing',
+    min_lr=0,
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=34)
+total_epochs = 256
+checkpoint_config = dict(interval=4)
+workflow = [('train', 1)]
+evaluation = dict(
+    interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
+log_config = dict(
+    interval=20,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        #    dict(type='TensorboardLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/slowfast_r101_r50_4x16x1_256e_kinetics400_rgb'
+load_from = None
+resume_from = None
+find_unused_parameters = False