Add configs for inference (open-mmlab#15)

* add configs for inference

* remove unused pipeline

configs/recognition/i3d/i3d_r50_video_inference_32x2x1_100e_kinetics400_rgb.py

@@ -0,0 +1,49 @@
+# model settings
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet3d',
+        pretrained2d=True,
+        pretrained='torchvision://resnet50',
+        depth=50,
+        conv_cfg=dict(type='Conv3d'),
+        norm_eval=False,
+        inflate=((1, 1, 1), (1, 0, 1, 0), (1, 0, 1, 0, 1, 0), (0, 1, 0)),
+        zero_init_residual=False),
+    cls_head=dict(
+        type='I3DHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        dropout_ratio=0.5,
+        init_std=0.01))
+# model training and testing settings
+test_cfg = dict(average_clips=None)
+# dataset settings
+dataset_type = 'VideoDataset'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
+test_pipeline = [
+    dict(type='DecordInit', num_threads=1),
+    dict(
+        type='SampleFrames',
+        clip_len=32,
+        frame_interval=2,
+        num_clips=1,
+        test_mode=True),
+    dict(type='DecordDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='ThreeCrop', crop_size=256),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW'),
+    dict(type='Collect', keys=['imgs'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+data = dict(
+    videos_per_gpu=1,
+    workers_per_gpu=2,
+    test=dict(
+        type=dataset_type,
+        ann_file=None,
+        data_prefix=None,
+        pipeline=test_pipeline))

configs/recognition/r2plus1d/r2plus1d_r34_video_inference_8x8x1_180e_kinetics400_rgb.py

@@ -0,0 +1,57 @@
+# model settings
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet2Plus1d',
+        depth=34,
+        pretrained=None,
+        pretrained2d=False,
+        norm_eval=False,
+        conv_cfg=dict(type='Conv2plus1d'),
+        norm_cfg=dict(type='SyncBN', requires_grad=True, eps=1e-3),
+        act_cfg=dict(type='ReLU'),
+        conv1_kernel=(3, 7, 7),
+        conv1_stride_t=1,
+        pool1_stride_t=1,
+        inflate=(1, 1, 1, 1),
+        spatial_strides=(1, 2, 2, 2),
+        temporal_strides=(1, 2, 2, 2),
+        zero_init_residual=False),
+    cls_head=dict(
+        type='I3DHead',
+        num_classes=400,
+        in_channels=512,
+        spatial_type='avg',
+        dropout_ratio=0.5,
+        init_std=0.01))
+# model training and testing settings
+train_cfg = None
+test_cfg = dict(average_clips=None)
+# dataset settings
+dataset_type = 'VideoDataset'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
+test_pipeline = [
+    dict(type='DecordInit'),
+    dict(
+        type='SampleFrames',
+        clip_len=8,
+        frame_interval=8,
+        num_clips=10,
+        test_mode=True),
+    dict(type='DecordDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='ThreeCrop', crop_size=256),
+    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=1,
+    workers_per_gpu=2,
+    test=dict(
+        type=dataset_type,
+        ann_file=None,
+        data_prefix=None,
+        pipeline=test_pipeline))

configs/recognition/slowfast/slowfast_r50_video_inference_4x16x1_256e_kinetics400_rgb.py

@@ -0,0 +1,68 @@
+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=50,
+            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))
+
+# model training and testing settings
+test_cfg = dict(average_clips=None)
+# dataset settings
+dataset_type = 'VideoDataset'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
+
+test_pipeline = [
+    dict(type='DecordInit'),
+    dict(
+        type='SampleFrames',
+        clip_len=32,
+        frame_interval=2,
+        num_clips=10,
+        test_mode=True),
+    dict(type='DecordDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='ThreeCrop', crop_size=256),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW'),
+    dict(type='Collect', keys=['imgs'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+
+data = dict(
+    videos_per_gpu=1,
+    workers_per_gpu=2,
+    test=dict(
+        type=dataset_type,
+        ann_file=None,
+        data_prefix=None,
+        pipeline=test_pipeline))

configs/recognition/slowonly/slowonly_r50_video_inference_4x16x1_256e_kinetics400_rgb.py

@@ -0,0 +1,47 @@
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet3dSlowOnly',
+        depth=50,
+        pretrained=None,
+        lateral=False,
+        conv1_kernel=(1, 7, 7),
+        conv1_stride_t=1,
+        pool1_stride_t=1,
+        inflate=(0, 0, 1, 1),
+        norm_eval=False),
+    cls_head=dict(
+        type='I3DHead',
+        in_channels=2048,
+        num_classes=400,
+        spatial_type='avg',
+        dropout_ratio=0.5))
+train_cfg = None
+test_cfg = dict(average_clips=None)
+dataset_type = 'VideoDataset'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
+test_pipeline = [
+    dict(type='DecordInit'),
+    dict(
+        type='SampleFrames',
+        clip_len=4,
+        frame_interval=16,
+        num_clips=10,
+        test_mode=True),
+    dict(type='DecordDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='ThreeCrop', crop_size=256),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW'),
+    dict(type='Collect', keys=['imgs'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+data = dict(
+    videos_per_gpu=1,
+    workers_per_gpu=2,
+    test=dict(
+        type=dataset_type,
+        ann_file=None,
+        data_prefix=None,
+        pipeline=test_pipeline))

configs/recognition/tsm/tsm_r50_video_inference_1x1x8_100e_kinetics400_rgb.py

@@ -0,0 +1,50 @@
+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='ResNetTSM',
+        pretrained='torchvision://resnet50',
+        depth=50,
+        norm_eval=False,
+        shift_div=8),
+    cls_head=dict(
+        type='TSMHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.5,
+        init_std=0.001,
+        is_shift=True))
+# model training and testing settings
+train_cfg = None
+test_cfg = dict(average_clips=None)
+# dataset settings
+dataset_type = 'VideoDataset'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
+test_pipeline = [
+    dict(type='DecordInit', num_threads=1),
+    dict(
+        type='SampleFrames',
+        clip_len=1,
+        frame_interval=1,
+        num_clips=8,
+        test_mode=True),
+    dict(type='DecordDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCHW'),
+    dict(type='Collect', keys=['imgs'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+
+data = dict(
+    videos_per_gpu=1,
+    workers_per_gpu=2,
+    test=dict(
+        type=dataset_type,
+        ann_file=None,
+        data_prefix=None,
+        pipeline=test_pipeline))

configs/recognition/tsn/tsn_r50_video_inference_1x1x3_100e_kinetics400_rgb.py

@@ -31,7 +31,6 @@
     dict(type='DecordDecode'),
     dict(type='Resize', scale=(-1, 256)),
     dict(type='TenCrop', crop_size=224),
-    dict(type='Flip', flip_ratio=0),
     dict(type='Normalize', **img_norm_cfg),
     dict(type='FormatShape', input_format='NCHW'),
     dict(type='Collect', keys=['imgs'], meta_keys=[]),