Update 256p performance (#132)

b127e4b3 · Jintao Lin · GitHub · 063ced55 · b127e4b3 · b127e4b3
11 changed file
--- a/configs/recognition/i3d/README.md
+++ b/configs/recognition/i3d/README.md
@@ -7,8 +7,11 @@
 |config | resolution | gpus | backbone |pretrain| top1 acc| top5 acc | inference_time(video/s) | gpu_mem(M)| ckpt | log| json|
 |:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
 |[i3d_r50_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb.py) |340x256|8| ResNet50|ImageNet |72.68|90.78|1.7 (320x3 frames)| 5170|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb/i3d_r50_32x2x1_100e_kinetics400_rgb_20200614-c25ef9a4.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb/20200614_060456.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb/20200614_060456.log.json)|
+|[i3d_r50_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb.py) |short-side 256|8| ResNet50|ImageNet | 73.27|90.92|x|5170|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_256p_32x2x1_100e_kinetics400_rgb/i3d_r50_256p_32x2x1_100e_kinetics400_rgb_20200801-7d9f44de.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_256p_32x2x1_100e_kinetics400_rgb/20200725_031555.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_256p_32x2x1_100e_kinetics400_rgb/20200725_031555.log.json)|
 |[i3d_r50_dense_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb.py) |340x256|8x2| ResNet50| ImageNet|72.77|90.57|1.7 (320x3 frames)| 5170| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb/i3d_r50_dense_32x2x1_100e_kinetics400_rgb_20200616-2bbb4361.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb/20200616_230011.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb/20200616_230011.log.json)|
+|[i3d_r50_dense_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb.py) |short-side 256|8| ResNet50| ImageNet|73.48|91.00|x| 5170| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_dense_256p_32x2x1_100e_kinetics400_rgb/i3d_r50_dense_256p_32x2x1_100e_kinetics400_rgb_20200725-24eb54cc.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_dense_256p_32x2x1_100e_kinetics400_rgb/20200725_031604.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_dense_256p_32x2x1_100e_kinetics400_rgb/20200725_031604.log.json)|
 |[i3d_r50_fast_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb.py) |340x256|8| ResNet50 |ImageNet|72.32|90.72|1.8 (320x3 frames)| 5170| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb/i3d_r50_fast_32x2x1_100e_kinetics400_rgb_20200612-000e4d2a.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb/20200612_233836.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb/20200612_233836.log.json)|
+|[i3d_r50_fast_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb.py) |short-side 256|8| ResNet50| ImageNet|73.24|90.99|x| 5170| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_fast_256p_32x2x1_100e_kinetics400_rgb/i3d_r50_fast_256p_32x2x1_100e_kinetics400_rgb_20200817-4e90d1d5.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_fast_256p_32x2x1_100e_kinetics400_rgb/20200725_031457.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/i3d/i3d_r50_fast_256p_32x2x1_100e_kinetics400_rgb/20200725_031457.log.json) |

 Notes:
 1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
@@ -44,7 +47,7 @@ Example: test I3D model on Kinetics-400 dataset and dump the result to a json fi
 ```shell
 python tools/test.py configs/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb.py \
    checkpoints/SOME_CHECKPOINT.pth --eval top_k_accuracy mean_class_accuracy \
-    --out result.json
+    --out result.json --average-clips prob
 ```

 For more details, you can refer to **Test a dataset** part in [getting_started](/docs/getting_started.md#test-a-dataset).
--- a/configs/recognition/r2plus1d/README.md
+++ b/configs/recognition/r2plus1d/README.md
@@ -6,6 +6,7 @@

 |config | resolution | gpus | backbone | pretrain| top1 acc| top5 acc | inference_time(video/s) | gpu_mem(M) | ckpt | log| json|
 |:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
+|[r2plus1d_r34_8x8x1_180e_kinetics400_rgb](/configs/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb.py) | short-side 256|8x4| ResNet34|None |67.30|87.65|x|5019|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/r2plus1d/r2plus1d_r34_256p_8x8x1_180e_kinetics400_rgb/r2plus1d_r34_256p_8x8x1_180e_kinetics400_rgb_20200729-aa94765e.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/r2plus1d/r2plus1d_r34_256p_8x8x1_180e_kinetics400_rgb/20200728_021421.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/r2plus1d/r2plus1d_r34_256p_8x8x1_180e_kinetics400_rgb/20200728_021421.log.json)|
 |[r2plus1d_r34_8x8x1_180e_kinetics400_rgb](/configs/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb.py) | short-side 320|8x2| ResNet34|None |68.68|88.36|1.6 (80x3 frames)|5019|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb/r2plus1d_r34_8x8x1_180e_kinetics400_rgb_20200618-3fce5629.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb/r21d_8x8.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb/r2plus1d_r34_8x8_69.58_88.36.log.json)|
 |[r2plus1d_r34_32x2x1_180e_kinetics400_rgb](/configs/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb.py) |short-side 320|8x2| ResNet34|None |74.60|91.59|0.5 (320x3 frames)|12975| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb/r2plus1d_r34_32x2x1_180e_kinetics400_rgb_20200618-63462eb3.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb/r21d_32x2.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb/r2plus1d_r34_32x2_74.6_91.6.log.json)|


--- a/configs/recognition/slowfast/README.md
+++ b/configs/recognition/slowfast/README.md
@@ -6,7 +6,9 @@

 |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 256|8x4| ResNet50|None |74.75|91.73|x|6203|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_256p_4x16x1_256e_kinetics400_rgb/slowfast_r50_256p_4x16x1_256e_kinetics400_rgb_20200728-145f1097.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_256p_4x16x1_256e_kinetics400_rgb/20200728_022505.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_256p_4x16x1_256e_kinetics400_rgb/20200728_022505.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 256|8x4| ResNet50 |None |75.61|92.34|x|9062|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_256p_8x8x1_256e_kinetics400_rgb/slowfast_r50_256p_8x8x1_256e_kinetics400_rgb_20200810-863812c2.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_256p_8x8x1_256e_kinetics400_rgb/20200731_151537.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.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://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:

--- a/configs/recognition/slowonly/README.md
+++ b/configs/recognition/slowonly/README.md
@@ -6,18 +6,21 @@

 |config | resolution | gpus | backbone |pretrain| top1 acc| top5 acc | inference_time(video/s) | gpu_mem(M) | ckpt | log| json|
 |:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
+|[slowonly_r50_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb.py)|short-side 256|8x4| ResNet50 | None |72.76|90.51|x|3168|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_256p_4x16x1_256e_kinetics400_rgb/slowonly_r50_256p_4x16x1_256e_kinetics400_rgb_20200820-bea7701f.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_256p_4x16x1_256e_kinetics400_rgb/20200817_001411.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_256p_4x16x1_256e_kinetics400_rgb/20200817_001411.log.json)|
+|[slowonly_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb.py) |short-side 256|8x4| ResNet50 | None |74.42|91.49|x|5820|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_256p_8x8x1_256e_kinetics400_rgb/slowonly_r50_256p_8x8x1_256e_kinetics400_rgb_20200820-75851a7d.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_256p_8x8x1_256e_kinetics400_rgb/20200817_003320.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_256p_8x8x1_256e_kinetics400_rgb/20200817_003320.log.json)|
 |[slowonly_r50_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb.py)|short-side 320|8x2| ResNet50 | None |73.02|90.77|4.0 (40x3 frames)|3168|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb/slowonly_r50_4x16x1_256e_kinetics400_rgb_20200704-a69556c6.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb/so_4x16.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb/slowonly_r50_4x16_73.02_90.77.log.json)|
 |[slowonly_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb.py) |short-side 320|8x3| ResNet50 | None |74.93|91.92|2.3 (80x3 frames)|5820| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb/slowonly_r50_8x8x1_256e_kinetics400_rgb_20200703-a79c555a.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb/so_8x8.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb/slowonly_r50_8x8_74.93_91.92.log.json)|
 |[slowonly_r50_4x16x1_256e_kinetics400_flow](/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow.py)|short-side 320|8x2| ResNet50  | ImageNet |61.79|83.62|x|8450| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow/slowonly_r50_4x16x1_256e_kinetics400_flow_20200704-decb8568.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow/slowonly_r50_4x16x1_256e_kinetics400_flow_61.8_83.6.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow/slowonly_r50_4x16x1_256e_kinetics400_flow_61.8_83.6.log.json)|
 |[slowonly_r50_8x8x1_196e_kinetics400_flow](/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow.py) |short-side 320|8x4| ResNet50 | ImageNet |65.76|86.25|x|8455| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow/slowonly_r50_8x8x1_256e_kinetics400_flow_20200704-6b384243.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow/slowonly_r50_8x8x1_196e_kinetics400_flow_65.8_86.3.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow/slowonly_r50_8x8x1_196e_kinetics400_flow_65.8_86.3.log.json)|

 ### Kinetics-400 Data Benchmark
-In data benchmark, we compare two different data preprocessing methods: (1) Resize video to 340x256, (2) Resize the short edge of video to 320px. 
+In data benchmark, we compare two different data preprocessing methods: (1) Resize video to 340x256, (2) Resize the short edge of video to 320px, (3) Resize the short edge of video to 256px.

 | config                                                       |   resolution   | gpus | backbone | Input | pretrain | top1 acc | top5 acc |  testing protocol  |                             ckpt                             |                             log                              |                             json                             |
 | :----------------------------------------------------------- | :------------: | :--: | :------: | :---: | :------: | :------: | :------: | :----------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
 | [slowonly_r50_randomresizedcrop_340x256_4x16x1_256e_kinetics400_rgb](data_benchmark/slowonly_r50_randomresizedcrop_340x256_4x16x1_256e_kinetics400_rgb.py) |    340x256     | 8x2  | ResNet50 | 4x16  |   None   |  71.61   |  90.05   | 10 clips x 3 crops | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/data_benchmark/slowonly_r50_randomresizedcrop_340x256_4x16x1_256e_kinetics400_rgb/slowonly_r50_randomresizedcrop_340x256_4x16x1_256e_kinetics400_rgb_20200803-dadca1a3.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/data_benchmark/slowonly_r50_randomresizedcrop_340x256_4x16x1_256e_kinetics400_rgb/slowonly_r50_randomresizedcrop_340x256_4x16x1_256e_kinetics400_rgb_20200803.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/data_benchmark/slowonly_r50_randomresizedcrop_340x256_4x16x1_256e_kinetics400_rgb/slowonly_r50_randomresizedcrop_340x256_4x16x1_256e_kinetics400_rgb_20200803.json) |
 | [slowonly_r50_randomresizedcrop_320p_4x16x1_256e_kinetics400_rgb](data_benchmark/slowonly_r50_randomresizedcrop_320p_4x16x1_256e_kinetics400_rgb.py) | short-side 320 | 8x2  | ResNet50 | 4x16  |   None   |  73.02   |  90.77   | 10 clips x 3 crops | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb/slowonly_r50_4x16x1_256e_kinetics400_rgb_20200704-a69556c6.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb/so_4x16.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb/slowonly_r50_4x16_73.02_90.77.log.json) |
+| [slowonly_r50_randomresizedcrop_256p_4x16x1_256e_kinetics400_rgb](data_benchmark/slowonly_r50_randomresizedcrop_256p_4x16x1_256e_kinetics400_rgb.py) | short-side 256 | 8x4  | ResNet50 | 4x16  |   None   |  72.76   |  90.51   | 10 clips x 3 crops | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_256p_4x16x1_256e_kinetics400_rgb/slowonly_r50_256p_4x16x1_256e_kinetics400_rgb_20200820-bea7701f.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_256p_4x16x1_256e_kinetics400_rgb/20200817_001411.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowonly/slowonly_r50_256p_4x16x1_256e_kinetics400_rgb/20200817_001411.log.json) |

 Notes:


--- a/configs/recognition/slowonly/data_benchmark/slowonly_r50_randomresizedcrop_256p_4x16x1_256e_kinetics400_rgb.py
+++ b/configs/recognition/slowonly/data_benchmark/slowonly_r50_randomresizedcrop_256p_4x16x1_256e_kinetics400_rgb.py
+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 = 'RawframeDataset'
+data_root = 'data/kinetics400/rawframes_train_256p'
+data_root_val = 'data/kinetics400/rawframes_val_256p'
+ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes_256p.txt'
+ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes_256p.txt'
+ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes_256p.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=4, frame_interval=16, 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=4,
+        frame_interval=16,
+        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=4,
+        frame_interval=16,
+        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=16,
+    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=0.6, 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)
+total_epochs = 256
+checkpoint_config = dict(interval=4)
+workflow = [('train', 1)]
+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'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/slowonly_r50_randomresizedcrop_256p_4x16x1'
+            '_256e_kinetics400_rgb')
+load_from = None
+resume_from = None
+find_unused_parameters = False
--- a/configs/recognition/tsm/README.md
+++ b/configs/recognition/tsm/README.md
@@ -7,9 +7,12 @@
 |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_1x1x8_50e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb.py) |short-side 256|8| ResNet50| ImageNet |70.59|89.52|x|x|x|7079|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_256p_1x1x8_50e_kinetics400_rgb/tsm_r50_256p_1x1x8_50e_kinetics400_rgb_20200726-020785e2.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_256p_1x1x8_50e_kinetics400_rgb/20200725_031623.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_256p_1x1x8_50e_kinetics400_rgb/20200725_031623.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_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb.py) |short-side 256|8| ResNet50 | ImageNet|73.38|91.02|x|x|x|7079|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_dense_256p_1x1x8_100e_kinetics400_rgb/tsm_r50_dense_256p_1x1x8_100e_kinetics400_rgb_20200727-e1e0c785.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_dense_256p_1x1x8_100e_kinetics400_rgb/20200725_032043.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_dense_256p_1x1x8_100e_kinetics400_rgb/20200725_032043.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)|
+|[tsm_r50_1x1x16_50e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb.py) |short-side 256|8| ResNet50| ImageNet |72.01|90.57|x|x|x|10398|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_256p_1x1x16_50e_kinetics400_rgb/tsm_r50_256p_1x1x16_50e_kinetics400_rgb_20200727-b414aa3c.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_256p_1x1x16_50e_kinetics400_rgb/20200725_031232.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_256p_1x1x16_50e_kinetics400_rgb/20200725_031232.log.json)|

 ### Something-Something V1


--- a/configs/recognition/tsn/README.md
+++ b/configs/recognition/tsn/README.md
@@ -13,10 +13,12 @@
 |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|
 |:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
 |[tsn_r50_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb.py) |340x256|8| ResNet50 | ImageNet|70.60|89.26|x|x|4.3 (25x10 frames)|8344| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb/tsn_r50_1x1x3_100e_kinetics400_rgb_20200614-e508be42.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb/20200614_063526.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb/20200614_063526.log.json)|
+|[tsn_r50_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb.py) |short-side 256|8| ResNet50 | ImageNet|70.42|89.03|x|x|x|8343|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_1x1x3_100e_kinetics400_rgb/tsn_r50_256p_1x1x3_100e_kinetics400_rgb_20200725-22592236.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_1x1x3_100e_kinetics400_rgb/20200725_031325.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_1x1x3_100e_kinetics400_rgb/20200725_031325.log.json)|
 |[tsn_r50_dense_1x1x5_50e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb.py) |340x256|8x3| ResNet50| ImageNet |70.18|89.10|[69.15](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#training)|[88.56](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#training)|12.7 (8x10 frames)|7028| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb/tsn_r50_dense_1x1x5_100e_kinetics400_rgb_20200627-a063165f.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb/20200627_105310.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb/20200627_105310.log.json)|
 |[tsn_r50_320p_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb.py) |short-side 320|8x2| ResNet50| ImageNet |70.91|89.51|x|x|10.7 (25x3 frames)| 8344 | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_320p_1x1x3_100e_kinetics400_rgb_20200702-cc665e2a.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_f3_kinetics400_shortedge_70.9_89.5.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_f3_kinetics400_shortedge_70.9_89.5.log.json)|
 |[tsn_r50_320p_1x1x3_110e_kinetics400_flow](/configs/recognition/tsn/tsn_r50_320p_1x1x3_110e_kinetics400_flow.py) |short-side 320|8x2| ResNet50 | ImageNet|55.70|79.85|x|x|x| 8471 | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_110e_kinetics400_flow/tsn_r50_320p_1x1x3_110e_kinetics400_flow_20200705-3036bab6.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_110e_kinetics400_flow/tsn_r50_f3_kinetics400_flow_shortedge_55.7_79.9.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_110e_kinetics400_flow/tsn_r50_f3_kinetics400_flow_shortedge_55.7_79.9.log.json)|
 |tsn_r50_320p_1x1x3_kinetics400_twostream [1: 1]* |x|x| ResNet50 | ImageNet|72.76|90.52| x | x | x | x  | x|x|x|
+|[tsn_r50_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb.py)|short-side 256|8| ResNet50| ImageNet |71.80|90.17|x|x|x|8343|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_1x1x8_100e_kinetics400_rgb/tsn_r50_256p_1x1x8_100e_kinetics400_rgb_20200817-883baf16.pth)|[log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_1x1x8_100e_kinetics400_rgb/20200815_173413.log)|[json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_1x1x8_100e_kinetics400_rgb/20200815_173413.log.json)|
 |[tsn_r50_320p_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb.py) |short-side 320|8x3| ResNet50| ImageNet |72.41|90.55|x|x|11.1 (25x3 frames)| 8344  | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb/tsn_r50_320p_1x1x8_100e_kinetics400_rgb_20200702-ef80e3d7.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb/tsn_r50_f8_kinetics400_shortedge_72.4_90.6.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb/tsn_r50_f8_kinetics400_shortedge_72.4_90.6.log.json)|
 |[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|
@@ -28,7 +30,10 @@ Here, We use [1: 1] to indicate that we combine rgb and flow score with coeffici

 ### Kinetics-400 Data Benchmark (8-gpus, ResNet50, ImageNet pretrain; 3 segments)

-In data benchmark, we compare: 1. Different data preprocessing methods: (1) Resize video to 340x256, (2) Resize the short edge of video to 320px; 2. Different data augmentation methods: (1) MultiScaleCrop, (2) RandomResizedCrop; 3. Different testing protocols: (1) 25 frames x 10 crops, (2) 25 frames x 3 crops.
+In data benchmark, we compare:
+1. Different data preprocessing methods: (1) Resize video to 340x256, (2) Resize the short edge of video to 320px, (3) Resize the short edge of video to 256px;
+2. Different data augmentation methods: (1) MultiScaleCrop, (2) RandomResizedCrop;
+3. Different testing protocols: (1) 25 frames x 10 crops, (2) 25 frames x 3 crops.

 |                            config                            |   resolution   | training augmentation | testing protocol | top1 acc | top5 acc |                             ckpt                             |                             log                              |                             json                             |
 | :----------------------------------------------------------: | :------------: | :-------------------: | :--------------: | :------: | :------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
@@ -40,6 +45,11 @@ In data benchmark, we compare: 1. Different data preprocessing methods: (1) Resi
 |                              x                               | short-side 320 |    MultiScaleCrop     |   25x3 frames    |  70.54   |  89.39   |                              x                               |                              x                               |                              x                               |
 | [tsn_r50_randomresizedcrop_320p_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/data_benchmark/tsn_r50_randomresizedcrop_320p_1x1x3_100e_kinetics400_rgb.py) | short-side 320 |   RandomResizedCrop   |   25x10 frames   |  70.44   |  89.23   | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_320p_1x1x3_100e_kinetics400_rgb_20200702-cc665e2a.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_f3_kinetics400_shortedge_70.9_89.5.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_f3_kinetics400_shortedge_70.9_89.5.log.json) |
 |                              x                               | short-side 320 |   RandomResizedCrop   |   25x3 frames    |  70.91   |  89.51   |                              x                               |                              x                               |                              x                               |
+| [tsn_r50_multiscalecrop_256p_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/data_benchmark/tsn_r50_multiscalecrop_256p_1x1x3_100e_kinetics400_rgb.py) | short-side 256 |    MultiScaleCrop     |   25x10 frames   |  70.42   |  89.03   | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_1x1x3_100e_kinetics400_rgb/tsn_r50_256p_1x1x3_100e_kinetics400_rgb_20200725-22592236.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_1x1x3_100e_kinetics400_rgb/20200725_031325.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_1x1x3_100e_kinetics400_rgb/20200725_031325.log.json)|
+|                              x                               | short-side 256 |    MultiScaleCrop     |   25x3 frames    |  70.79   |  89.42   |                              x                               |                              x                               |                              x                               |
+| [tsn_r50_randomresizedcrop_256p_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/data_benchmark/tsn_r50_randomresizedcrop_256p_1x1x3_100e_kinetics400_rgb.py) | short-side 256 |    RandomResizedCrop     |   25x10 frames   |  69.80   |  89.06   | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_randomresize_1x1x3_100e_kinetics400_rgb/tsn_r50_256p_randomresize_1x1x3_100e_kinetics400_rgb_20200817-ae7963ca.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_randomresize_1x1x3_100e_kinetics400_rgb/20200815_172601.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_256p_randomresize_1x1x3_100e_kinetics400_rgb/20200815_172601.log.json)|
+|                              x                               | short-side 256 |   RandomResizedCrop   |   25x3 frames    |  70.48   |  89.89   |                              x                               |                              x                               |                              x                               |
+

 ### Something-Something V1


--- a/configs/recognition/tsn/data_benchmark/tsn_r50_multiscalecrop_256p_1x1x3_100e_kinetics400_rgb.py
+++ b/configs/recognition/tsn/data_benchmark/tsn_r50_multiscalecrop_256p_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_256p'
+data_root_val = 'data/kinetics400/rawframes_val_256p'
+ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes_256p.txt'
+ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes_256p.txt'
+ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes_256p.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=1, frame_interval=1, num_clips=3),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(
+        type='MultiScaleCrop',
+        input_size=224,
+        scales=(1, 0.875, 0.75, 0.66),
+        random_crop=False,
+        max_wh_scale_gap=1),
+    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='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='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='RawFrameDecode'),
+    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', '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'),
+    ])
+# runtime settings
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/tsn_r50_multiscalecrop_256p_1x1x3'
+            '_100e_kinetics400_rgb/')
+load_from = None
+resume_from = None
+workflow = [('train', 5)]
--- a/configs/recognition/tsn/data_benchmark/tsn_r50_randomresizedcrop_256p_1x1x3_100e_kinetics400_rgb.py
+++ b/configs/recognition/tsn/data_benchmark/tsn_r50_randomresizedcrop_256p_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_256p'
+data_root_val = 'data/kinetics400/rawframes_val_256p'
+ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes_256p.txt'
+ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes_256p.txt'
+ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes_256p.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=1, frame_interval=1, num_clips=3),
+    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='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='RawFrameDecode'),
+    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='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='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)  # 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='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_randomresizedcrop_256p_1x1x3'
+            '_100e_kinetics400_rgb/')
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
--- a/configs/recognition/tsn/data_benchmark/tsn_r50_test_256p_1x1x25_10crop_100e_kinetics400_rgb.py
+++ b/configs/recognition/tsn/data_benchmark/tsn_r50_test_256p_1x1x25_10crop_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_val = 'data/kinetics400/rawframes_val_256p'
+ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes_256p.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')
+test_pipeline = [
+    dict(
+        type='SampleFrames',
+        clip_len=1,
+        frame_interval=1,
+        num_clips=25,
+        test_mode=True),
+    dict(type='RawFrameDecode'),
+    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', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+data = dict(
+    workers_per_gpu=4,
+    test=dict(
+        type=dataset_type,
+        ann_file=ann_file_test,
+        data_prefix=data_root_val,
+        pipeline=test_pipeline))
+dist_params = dict(backend='nccl')
--- a/configs/recognition/tsn/data_benchmark/tsn_r50_test_256p_1x1x25_3crop_100e_kinetics400_rgb.py
+++ b/configs/recognition/tsn/data_benchmark/tsn_r50_test_256p_1x1x25_3crop_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_val = 'data/kinetics400/rawframes_val_256p'
+ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes_256p.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')
+test_pipeline = [
+    dict(
+        type='SampleFrames',
+        clip_len=1,
+        frame_interval=1,
+        num_clips=25,
+        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='NCHW'),
+    dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
+    dict(type='ToTensor', keys=['imgs'])
+]
+data = dict(
+    workers_per_gpu=4,
+    test=dict(
+        type=dataset_type,
+        ann_file=ann_file_test,
+        data_prefix=data_root_val,
+        pipeline=test_pipeline))
+dist_params = dict(backend='nccl')