Retest tsn and tsm video ckpts

configs/recognition/slowfast/README.md

@@ -6,7 +6,7 @@
 
 |config | resolution | gpus | backbone |pretrain| top1 acc| top5 acc | inference_time(video/s) | gpu_mem(M) | ckpt | log| json|
 |:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
-|[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://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/slowfast_r50_4x16x1_256e_kinetics400_rgb_20200704-bcde7ed7.pth）| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/20200704_232901.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/20200704_232901.log.json)|
+|[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://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/slowfast_r50_4x16x1_256e_kinetics400_rgb_20200704-bcde7ed7.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/20200704_232901.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.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 320|8x3| ResNet50 |None|76.94|92.8|1.3 ((32+8)x10x3 frames)|9062| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/slowfast_r50_8x8x1_256e_kinetics400_rgb_20200716-73547d2b.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/20200716_192653.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/20200716_192653.log.json)|
 
 Notes:

configs/recognition/tsm/README.md

@@ -7,6 +7,7 @@
 |config | resolution | gpus | backbone | pretrain | top1 acc| top5 acc | reference top1 acc | reference top5 acc | inference_time(video/s) | gpu_mem(M)| ckpt | log| json|
 |:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
 |[tsm_r50_1x1x8_50e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb.py) |340x256|8| ResNet50| ImageNet |70.24|89.56|[70.36](https://github.com/mit-han-lab/temporal-shift-module/blob/8d53d6fda40bea2f1b37a6095279c4b454d672bd/scripts/train_tsm_kinetics_rgb_8f.sh)|[89.49](https://github.com/mit-han-lab/temporal-shift-module/blob/8d53d6fda40bea2f1b37a6095279c4b454d672bd/scripts/train_tsm_kinetics_rgb_8f.sh)|74.0 (8x1 frames)| 7079 | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb/tsm_r50_1x1x8_50e_kinetics400_rgb_20200607-af7fb746.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb/20200607_211800.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb/20200607_211800.log.json)|
+|[tsm_r50_video_1x1x8_50e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_video_1x1x8_50e_kinetics400_rgb.py) |short-side 256|8| ResNet50| ImageNet |70.25|89.66|[70.36](https://github.com/mit-han-lab/temporal-shift-module/blob/8d53d6fda40bea2f1b37a6095279c4b454d672bd/scripts/train_tsm_kinetics_rgb_8f.sh)|[89.49](https://github.com/mit-han-lab/temporal-shift-module/blob/8d53d6fda40bea2f1b37a6095279c4b454d672bd/scripts/train_tsm_kinetics_rgb_8f.sh)|74.0 (8x1 frames)| 7077 | [ckpt]( https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_video_1x1x8_100e_kinetics400_rgb/tsm_r50_video_1x1x8_100e_kinetics400_rgb_20200702-a77f4328.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_video_1x1x8_100e_kinetics400_rgb/tsm_r50_video_2d_1x1x8_50e_kinetics400_rgb.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_video_1x1x8_100e_kinetics400_rgb/tsm_r50_video_2d_1x1x8_50e_kinetics400_rgb.log.json)|
 |[tsm_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb.py) |340x256|8x4| ResNet50 | ImageNet|72.9|90.44|[72.22](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#dense-sample)|[90.37](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#dense-sample)|11.5 (8x10 frames)| 7079 | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb/tsm_r50_dense_1x1x8_100e_kinetics400_rgb_20200626-91a54551.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb/20200626_213415.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb/20200626_213415.log.json)|
 |[tsm_r50_1x1x16_50e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb.py) |340x256|8| ResNet50| ImageNet |71.69|90.4|[70.67](https://github.com/mit-han-lab/temporal-shift-module/blob/8d53d6fda40bea2f1b37a6095279c4b454d672bd/scripts/train_tsm_kinetics_rgb_16f.sh)|[89.98](https://github.com/mit-han-lab/temporal-shift-module/blob/8d53d6fda40bea2f1b37a6095279c4b454d672bd/scripts/train_tsm_kinetics_rgb_16f.sh)|47.0 (16x1 frames)| 10404  | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb/tsm_r50_1x1x16_50e_kinetics400_rgb_20200607-f731bffc.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb/20200607_221310.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb/20200607_221310.log.json)|
 

configs/recognition/tsm/tsm_r50_video_1x1x8_100e_kinetics400_rgb.py → configs/recognition/tsm/tsm_r50_video_1x1x8_50e_kinetics400_rgb.py

@@ -130,7 +130,7 @@
 # runtime settings
 dist_params = dict(backend='nccl')
 log_level = 'INFO'
-work_dir = './work_dirs/tsm_r50_video_2d_1x1x8_100e_kinetics400_rgb/'
+work_dir = './work_dirs/tsm_r50_video_2d_1x1x8_50e_kinetics400_rgb/'
 load_from = None
 resume_from = None
 workflow = [('train', 1)]

configs/recognition/tsn/README.md

@@ -21,8 +21,8 @@
 |[tsn_r50_320p_1x1x8_110e_kinetics400_flow](/configs/recognition/tsn/tsn_r50_320p_1x1x8_110e_kinetics400_flow.py) |short-side 320|8x4| ResNet50 | ImageNet|57.76|80.99|x|x|x| 8473 | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x8_110e_kinetics400_flow/tsn_r50_320p_1x1x8_110e_kinetics400_flow_20200705-1f39486b.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x8_110e_kinetics400_flow/tsn_r50_f8_kinetics400_flow_shortedge_57.8_81.0.log)  | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x8_110e_kinetics400_flow/tsn_r50_f8_kinetics400_flow_shortedge_57.8_81.0.log.json)|
 |tsn_r50_320p_1x1x8_kinetics400_twostream [1: 1]* |x|x| ResNet50| ImageNet |74.64|91.77| x | x | x | x | x|x|x|
 |[tsn_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x8_100e_kinetics400_rgb.py) |340x256|8| ResNet50 | ImageNet|70.77|89.3|[68.75](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#training)|[88.42](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#training)|12.2 (8x10 frames)|8344| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_dense_1x1x8_100e_kinetics400_rgb/tsn_r50_dense_1x1x8_100e_kinetics400_rgb_20200606-e925e6e3.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_dense_1x1x8_100e_kinetics400_rgb/20200606_003901.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_dense_1x1x8_100e_kinetics400_rgb/20200606_003901.log.json)|
-|[tsn_r50_video_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics400_rgb.py) |340x256|8| ResNet50| ImageNet | 69.22 | 88.69 |x|x|x|21558| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics400_rgb/tsn_r50_video_1x1x8_100e_kinetics400_rgb_20200702-568cde33.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics400_rgb/tsn_r50_video_2d_1x1x8_100e_kinetics400_rgb.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics400_rgb/tsn_r50_video_2d_1x1x8_100e_kinetics400_rgb.log.json)|
-|[tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb.py) |340x256|8| ResNet50| ImageNet | 70.21 | 89.00 |x|x|x|21553| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb_20200703-0f19175f.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb/tsn_r50_video_2d_1x1x8_dense_100e_kinetics400_rgb.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb/tsn_r50_video_2d_1x1x8_dense_100e_kinetics400_rgb.log.json)|
+|[tsn_r50_video_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics400_rgb.py) |short-side 256|8| ResNet50| ImageNet | 71.79 | 90.25 |x|x|x|21558| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics400_rgb/tsn_r50_video_1x1x8_100e_kinetics400_rgb_20200702-568cde33.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics400_rgb/tsn_r50_video_2d_1x1x8_100e_kinetics400_rgb.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics400_rgb/tsn_r50_video_2d_1x1x8_100e_kinetics400_rgb.log.json)|
+|[tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb.py) |short-side 256|8| ResNet50| ImageNet | 70.4 | 89.12 |x|x|x|21553| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb_20200703-0f19175f.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb/tsn_r50_video_2d_1x1x8_dense_100e_kinetics400_rgb.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb/tsn_r50_video_2d_1x1x8_dense_100e_kinetics400_rgb.log.json)|
 
 Here, We use [1: 1] to indicate that we combine rgb and flow score with coefficients 1: 1 to get the two-stream prediction (without applying softmax).
 

configs/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics400_rgb.py

@@ -77,7 +77,7 @@
         test_mode=True),
     dict(type='DecordDecode'),
     dict(type='Resize', scale=(-1, 256)),
-    dict(type='TenCrop', crop_size=224),
+    dict(type='ThreeCrop', crop_size=256),
     dict(type='Flip', flip_ratio=0),
     dict(type='Normalize', **img_norm_cfg),
     dict(type='FormatShape', input_format='NCHW'),

configs/recognition/tsn/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb.py

@@ -72,7 +72,7 @@
         type='DenseSampleFrames',
         clip_len=1,
         frame_interval=1,
-        num_clips=25,
+        num_clips=8,
         start_index=0,
         test_mode=True),
     dict(type='DecordDecode'),