Merge branch 'ljt/add_additional_col' into 'master'

Add additional col for original repo results

See merge request open-mmlab/mmaction-lite!368

configs/recognition/tsm/README.md

@@ -4,24 +4,24 @@
 
 ### Kinetics-400
 
-|config | gpus | backbone | pretrain | top1 acc| 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) |8| ResNet50| ImageNet |70.24 (70.36)|89.56 (89.49)|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_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb.py) |8x4| ResNet50 | ImageNet|72.9 (72.22)|90.44 (90.37)|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) |8| ResNet50| ImageNet |71.69 (70.67)|90.4 (89.98)|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)|
+|config | 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) |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_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb.py) |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) |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)|
 
 ### Something-Something V1
 
-|config | gpus | backbone| pretrain | top1 acc| top5 acc | gpu_mem(M)  | ckpt | log| json|
-|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
-|[tsm_r50_1x1x8_50e_sthv1_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb.py) |8| ResNet50 | ImageNet|44.62 (42.08)|75.51 (72.66)| 7077| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb/tsm_r50_1x1x8_50e_sthv1_rgb_20200616-3417f361.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb/20200616_022852.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb/20200616_022852.log.json)|
+|config | gpus | backbone| pretrain | top1 acc| top5 acc | reference top1 acc | reference top5 acc | gpu_mem(M)  | ckpt | log| json|
+|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
+|[tsm_r50_1x1x8_50e_sthv1_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb.py) |8| ResNet50 | ImageNet|44.62|75.51|[42.08](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#training)|[72.66](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#training)| 7077| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb/tsm_r50_1x1x8_50e_sthv1_rgb_20200616-3417f361.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb/20200616_022852.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb/20200616_022852.log.json)|
 
 ### Something-Something V2
 
-|config | gpus | backbone | pretrain| top1 acc| top5 acc | gpu_mem(M)  | ckpt | log| json|
-|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
-|[tsm_r50_1x1x16_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb.py) |8| ResNet50| ImageNet |57.68 (56.57)|83.65 (84.30)| 10400| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb/tsm_r50_1x1x16_50e_sthv2_rgb_20200621-60ff441a.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb/20200621_101921.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb/20200621_101921.log.json)|
-|[tsm_r101_1x1x8_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb.py) |8| ResNet101 | ImageNet|59.12 (59.20)|85.74 (85.27)| 9784 | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb/tsm_r101_1x1x8_50e_sthv2_rgb_20200625-df82f5e6.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb/20200625_224131.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb/20200625_224131.log.json)|
+|config | gpus | backbone | pretrain| top1 acc| top5 acc |  reference top1 acc | reference top5 acc | gpu_mem(M)  | ckpt | log| json|
+|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
+|[tsm_r50_1x1x16_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb.py) |8| ResNet50| ImageNet |57.68 |83.65 |[56.57](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#training)|[84.30](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#training)| 10400| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb/tsm_r50_1x1x16_50e_sthv2_rgb_20200621-60ff441a.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb/20200621_101921.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb/20200621_101921.log.json)|
+|[tsm_r101_1x1x8_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb.py) |8| ResNet101 | ImageNet|59.12|85.74|[59.20](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#training)|[85.27](https://github.com/mit-han-lab/temporal-shift-module/tree/8d53d6fda40bea2f1b37a6095279c4b454d672bd#training)| 9784 | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb/tsm_r101_1x1x8_50e_sthv2_rgb_20200625-df82f5e6.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb/20200625_224131.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb/20200625_224131.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.
@@ -29,7 +29,7 @@ According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you ma
 e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
 2. The **inference_time** is got by this [benchmark script](/tools/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
 not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
-3. The values in brackets are the results got by training on the [original repo](https://github.com/mit-han-lab/temporal-shift-module), using the same model settings.
+3. The values in columns named after "reference" are the results got by training on the original repo, using the same model settings.
 
 For more details on data preparation, you can refer to Kinetics400, Something-Something V1 and Something-Something V2 in [Data Preparation](/docs/data_preparation.md).