提交 cc20f60d 编写于 作者: L linjintao

Merge branch 'tjq/modelzoo_paths' into 'master'

Add modelzoo paths

See merge request open-mmlab/mmaction-lite!345
......@@ -6,7 +6,7 @@
|config | gpus | pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|[bmn_400x100_9e_2x8_activitynet_feature](/configs/localization/bmn/bmn_400x100_2x8_9e_activitynet_feature.py) |2| None |75.28|67.22|5420|3.27|[ckpt]()| [log]()| [json]()|
|[bmn_400x100_9e_2x8_activitynet_feature](/configs/localization/bmn/bmn_400x100_2x8_9e_activitynet_feature.py) |2| None |75.28|67.22|5420|3.27|[ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature_20200619-42a3b111.pth)| [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature.log.json)|
Notes:
1. The **gpus** indicates the number of gpu we used to get the checkpoint.
......
......@@ -6,7 +6,7 @@
|config | gpus| pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|bsn_400x100_1x16_20e_activitynet_feature |1| None |74.65|66.45|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem]() [ckpt_pem]()| [log_tem]() [log_pem]()| [json_tem]() [json_pem]()||
|bsn_400x100_1x16_20e_activitynet_feature |1| None |74.65|66.45|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature_20200619-cd6accc3.pth) [ckpt_pem](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature_20200619-6111891d.pth)| [log_tem](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature.log) [log_pem](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature.log)| [json_tem](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature.log.json) [json_pem](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature.log.json)||
Notes:
1. The **gpus** indicates the number of gpu we used to get the checkpoint.
......
......@@ -6,11 +6,11 @@
|config | gpus | backbone |pretrain| top1 acc| top5 acc | inference_time(video/s) | gpu_mem(M)| ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|[i3d_r34_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r34_32x2x1_100e_kinetics400_rgb.py) |8| ResNet34|ImageNet |68.37|88.15|1.6 (320x3 frames)| 3176| [ckpt]() | [log]()| [json]()|
|[i3d_r50_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb.py) |8| ResNet50|ImageNet |72.68|90.78|1.7 (320x3 frames)| 5170|[ckpt]() | [log]()| [json]()|
|[i3d_r50_dense_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb.py) |8x2| ResNet50| ImageNet|72.77|90.57|1.7 (320x3 frames)| 5170| [ckpt]() | [log]()| [json]()|
|[i3d_r50_fast_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb.py) |8| ResNet50 |ImageNet|72.32|90.72|1.8 (320x3 frames)| 5170| [ckpt]() | [log]()| [json]()|
|[i3d_r50_video_3d_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_video_32x2x1_100e_kinetics400_rgb.py) |8| ResNet50| ImageNet| x | x | x| x| [ckpt]() | [log]()| [json]()|
|[i3d_r34_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r34_32x2x1_100e_kinetics400_rgb.py) |x| ResNet34|ImageNet |68.37|88.15|1.6 (320x3 frames)| 3176| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r34_32x2x1_100e_kinetics400_rgb/i3d_r34_32x2x1_100e_kinetics400_rgb_20200612-c883432b.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r34_32x2x1_100e_kinetics400_rgb/20200612_083439.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r34_32x2x1_100e_kinetics400_rgb/20200612_083439.log.json)|
|[i3d_r50_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb.py) |x| ResNet50|ImageNet |72.68|90.78|1.7 (320x3 frames)| 5170|[ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb/i3d_r50_32x2x1_100e_kinetics400_rgb_20200614-c25ef9a4.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb/20200614_060456.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb/20200614_060456.log.json)|
|[i3d_r50_dense_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb.py) |x| ResNet50| ImageNet|72.77|90.57|1.7 (320x3 frames)| 5170| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb/i3d_r50_dense_32x2x1_100e_kinetics400_rgb_20200616-2bbb4361.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb/20200616_230011.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb/20200616_230011.log.json)|
|[i3d_r50_fast_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb.py) |x| ResNet50 |ImageNet|72.32|90.72|1.8 (320x3 frames)| 5170| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb/i3d_r50_fast_32x2x1_100e_kinetics400_rgb_20200612-000e4d2a.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb/20200612_233836.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb/20200612_233836.log.json)|
|[i3d_r50_video_3d_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_video_32x2x1_100e_kinetics400_rgb.py) |x| ResNet50| ImageNet| x | x | x| x| [ckpt]() | [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.
......
......@@ -6,8 +6,8 @@
|config | 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) |8x2| ResNet34|None |68.68|88.36|1.6 (80x3 frames)|5019|[ckpt]()| [log]()| [json]()|
|[r2plus1d_r34_32x2x1_180e_kinetics400_rgb](/configs/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb.py) |8x2| ResNet34|None |74.60|91.59|0.5 (320x3 frames)|12975| [ckpt]() | [log]()| [json]()|
|[r2plus1d_r34_8x8x1_180e_kinetics400_rgb](/configs/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb.py) |x| ResNet34|None |68.68|88.36|1.6 (80x3 frames)|5019|[ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb/r2plus1d_r34_8x8x1_180e_kinetics400_rgb_20200618-3fce5629.pth)| [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb/r21d_8x8.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/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) |x| ResNet34|None |74.60|91.59|0.5 (320x3 frames)|12975| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb/r2plus1d_r34_32x2x1_180e_kinetics400_rgb_20200618-63462eb3.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb/r21d_32x2.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb/r2plus1d_r34_32x2_74.6_91.6.log.json)|
|[r2plus1d_r34_video_8x8x1_180e_kinetics400_rgb](/configs/recognition/r2plus1d/r2plus1d_r34_video_8x8x1_180e_kinetics400_rgb.py) |x| ResNet34|None |x|x|x|x| [ckpt]() | [log]()| [json]()|
Notes:
......
......@@ -6,8 +6,8 @@
|config | 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) |7x3| ResNet50|None |75.3|92.2|1.6 (320x3 frames)|6203|[ckpt]()| [log]()| [json]()|
|[slowfast_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py) |8x4| ResNet50 |None|76.36|92.56|1.3 (320x3 frames)|9062| [ckpt]() | [log]()| [json]()|
|[slowfast_r50_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py) |x| ResNet50|None |75.3|92.2|1.6 (320x3 frames)|6203|[ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/slowfast_r50_4x16x1_256e_kinetics400_rgb_20200618-9a124260.pth)| [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/sf_4x16.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/slowfast_r50_4x16_75.3_92.2.log.json)|
|[slowfast_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py) |x| ResNet50 |None|76.36|92.56|1.3 (320x3 frames)|9062| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/slowfast_r50_8x8x1_256e_kinetics400_rgb_20200619-ecd36535.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/sf_8x8.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/slowfast_r50_8x8_76.36_92.56.log.json)|
|[slowfast_r50_video_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_video_4x16x1_256e_kinetics400_rgb.py) |x| ResNet50|None |x|x|x|x| [ckpt]() | [log]()| [json]()|
Notes:
......
......@@ -6,11 +6,11 @@
|config | 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)|8x2| ResNet50 | None |73.02|90.77|4.0 (40x3 frames)|3168|[ckpt]()| [log]()| [json]()|
|[slowonly_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb.py) |8x3| ResNet50 | None |74.93|91.92|2.3 (80x3 frames)|5820| [ckpt]() | [log]()| [json]()|
|[slowonly_r50_4x16x1_256e_kinetics400_flow](/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow.py)|8x2| ResNet50 | ImageNet |61.79|83.62|x|8450| [ckpt]() | [log]() | [json]()|
|[slowonly_r50_8x8x1_196e_kinetics400_flow](/configs/recognition/slowonly/slowonly_r50_8x8x1_196e_kinetics400_flow.py) |8x4| ResNet50 | ImageNet |65.76|86.25|x|8455| [ckpt]() | [log]() | [json]()|
|[slowonly_r50_video_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowonly/slowonly_r50_video_4x16x1_256e_kinetics400_rgb.py)|x| ResNet50 | None |x|x|x|x| [ckpt]() | [log]()| [json]()|
|[slowonly_r50_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb.py)|x| ResNet50 | None |73.02|90.77|4.0 (40x3 frames)|3168|[ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb/slowonly_r50_4x16x1_256e_kinetics400_rgb_20200704-a69556c6.pth)| [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb/so_4x16.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb/slowonly_r50_4x16_74.93_91.92.log.json)|
|[slowonly_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb.py) |x| ResNet50 | None |74.93|91.92|2.3 (80x3 frames)|5820| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb/slowonly_r50_8x8x1_256e_kinetics400_rgb_20200703-a79c555a.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb/so_8x8.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb/slowonly_r50_8x8_73.02_90.77.log.json)|
|[slowonly_r50_4x16x1_256e_kinetics400_flow](/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow.py)|x| ResNet50 | ImageNet |61.79|83.62|x|8450| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow/slowonly_r50_4x16x1_256e_kinetics400_flow_20200704-decb8568.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow/slowonly_r50_4x16x1_256e_kinetics400_flow_61.8_83.6.log) | [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/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_196e_kinetics400_flow.py) |x| ResNet50 | ImageNet |65.76|86.25|x|8455| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow/slowonly_r50_8x8x1_256e_kinetics400_flow_20200704-6b384243.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow/slowonly_r50_8x8x1_196e_kinetics400_flow_65.8_86.3.log) | [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow/slowonly_r50_8x8x1_196e_kinetics400_flow_65.8_86.3.log.json)|
|[slowonly_r50_video_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowonly/slowonly_r50_video_4x16x1_256e_kinetics400_rgb.py)|x| ResNet50 | None |x|x|x|x| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)|
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.
......
......@@ -6,26 +6,26 @@
|config | gpus | backbone | pretrain | top1 acc| top5 acc | inference_time(video/s) | gpu_mem(M)| ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|[tsm_r50_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb.py) |8| ResNet50| ImageNet |70.24|89.56|74.0 (8x1 frames)| 7079 | [ckpt]() | [log]()| [json]()|
|[tsm_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb.py) |8x4| ResNet50 | ImageNet|71.84|90.18|11.5 (8x10 frames)| 7079 | [ckpt]() | [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|47.0 (16x1 frames)| 10404 | [ckpt]() | [log]()| [json]()|
|[tsm_r50_video_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_video_1x1x8_100e_kinetics400_rgb.py) |x| ResNet50| ImageNet | x | x | x | 7077 | [ckpt]() | [log]()| [json]()|
|[tsm_r50_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb.py) |x| ResNet50| ImageNet |70.24|89.56|74.0 (8x1 frames)| 7079 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb/tsm_r50_1x1x8_50e_kinetics400_rgb_20200607-af7fb746.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb/20200607_211800.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/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) |x| ResNet50 | ImageNet|71.84|90.18|11.5 (8x10 frames)| 7079 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb/tsm_r50_dense_1x1x8_100e_kinetics400_rgb_20200626-91a54551.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb/20200621_101921.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb/20200621_101921.log.json)|
|[tsm_r50_1x1x16_50e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb.py) |x| ResNet50| ImageNet |71.69|90.4|47.0 (16x1 frames)| 10404 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb/tsm_r50_1x1x16_50e_kinetics400_rgb_20200607-f731bffc.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb/20200607_221310.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb/20200607_221310.log.json)|
|[tsm_r50_video_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_video_1x1x8_100e_kinetics400_rgb.py) |x| ResNet50| ImageNet | x | x | x | 7077 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)|
### 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|75.51| 7077| [ckpt]() | [log]()| [json]()|
|[tsm_r50_1x1x16_50e_sthv1_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv1_rgb.py) |x| ResNet50 | ImageNet|43.81|74.73| x | [ckpt]() | [log]()| [json]()|
|[tsm_r101_1x1x8_50e_sthv1_rgb](/configs/recognition/tsm/tsm_r101_1x1x8_50e_sthv1_rgb.py) |x| ResNet101| ImageNet |46.41|74.07| x | [ckpt]() | [log]()| [json]()|
|[tsm_r50_1x1x8_50e_sthv1_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb.py) |x| ResNet50 | ImageNet|44.62|75.51| 7077| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb/tsm_r50_1x1x8_50e_sthv1_rgb_20200616-3417f361.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb/20200616_022852.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb/20200616_022852.log.json)|
|[tsm_r50_1x1x16_50e_sthv1_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv1_rgb.py) |x| ResNet50 | ImageNet|43.81|74.73| x | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)|
|[tsm_r101_1x1x8_50e_sthv1_rgb](/configs/recognition/tsm/tsm_r101_1x1x8_50e_sthv1_rgb.py) |x| ResNet101| ImageNet |46.41|74.07| x | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)|
### Something-Something V2
|config | gpus | backbone | pretrain| top1 acc| top5 acc | gpu_mem(M) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|[tsm_r50_1x1x8_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv2_rgb.py) |x| ResNet50| ImageNet |59.91|84.61| x| [ckpt]() | [log]()| [json]()|
|[tsm_r50_1x1x16_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb.py) |8| ResNet50| ImageNet |56.10|84.43| 10400| [ckpt]() | [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| 9784 | [ckpt]() | [log]()| [json]()|
|[tsm_r50_1x1x8_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv2_rgb.py) |x| ResNet50| ImageNet |59.91|84.61| x| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)|
|[tsm_r50_1x1x16_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb.py) |x| ResNet50| ImageNet |56.10|84.43| 10400| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb/tsm_r50_1x1x16_50e_sthv2_rgb_20200621-60ff441a.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb/20200621_101921.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/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) |x| ResNet101 | ImageNet|59.12|85.74| 9784 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb/tsm_r101_1x1x8_50e_sthv2_rgb_20200625-df82f5e6.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb/20200625_224131.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/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.
......
......@@ -6,24 +6,24 @@
|config | gpus | backbone | pretrain | top1 acc| top5 acc | gpu_mem(M) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|[tsn_r50_1x1x3_100e_ucf101_rgb](/configs/recognition/tsn/tsn_r50_1x1x3_80e_ucf101_rgb.py) |8| ResNet50 | ImageNet |80.12|96.09|8332| [ckpt]() | [log]()| [json]()|
|[tsn_r50_1x1x3_100e_ucf101_rgb](/configs/recognition/tsn/tsn_r50_1x1x3_80e_ucf101_rgb.py) |x| ResNet50 | ImageNet |80.12|96.09|8332| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x3_80e_ucf101_rgb/tsn_r50_1x1x3_80e_ucf101_rgb_20200613-d6ad9c48.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x3_80e_ucf101_rgb/20200613_020013.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x3_80e_ucf101_rgb/20200613_020013.log.json)|
### Kinetics-400
|config | gpus | backbone|pretrain | top1 acc| 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) |8| ResNet50 | ImageNet|70.60|89.26|4.3 (25x10 frames)|8344| [ckpt]() | [log]()| [json]()|
|[tsn_r50_1x1x5_50e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x5_50e_kinetics400_rgb.py) |8| ResNet50| ImageNet |68.64|88.19|86.7 (8x1 frames)|7031| [ckpt]() | [log]()| [json]()|
|[tsn_r50_dense_1x1x5_50e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb.py) |8x3| ResNet50| ImageNet |68.59|88.31|12.7 (8x10 frames)|7028| [ckpt]() | [log]()| [json]()|
|[tsn_r50_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x8_100e_kinetics400_rgb.py) |x| ResNet50| ImageNet |69.41|88.37|81.6 (8x1 frames)| x | [ckpt]() | [log]()| [json]()|
|[tsn_r50_320p_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb.py) |8x2| ResNet50| ImageNet |70.91|89.51|10.7 (25x3 frames)| 8344 | [ckpt]() | [log]() | [json]()|
|[tsn_r50_320p_1x1x3_110e_kinetics400_flow](/configs/recognition/tsn/tsn_r50_320p_1x1x3_110e_kinetics400_flow.py) |8x2| ResNet50 | ImageNet|55.70|79.85|x| 8471 | [ckpt]() | [log]() | [json]()|
|tsn_r50_320p_1x1x3_kinetics400_twostream [1: 1]* |x| ResNet50 | ImageNet|72.76|90.52| x | x | [ckpt]() | [log]() | [json]()|
|[tsn_r50_320p_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb.py) |8x3| ResNet50| ImageNet |72.41|90.55|11.1 (25x3 frames)| 8344 | [ckpt]() | [log]() | [json]()|
|[tsn_r50_320p_1x1x8_110e_kinetics400_flow](/configs/recognition/tsn/tsn_r50_320p_1x1x8_110e_kinetics400_flow.py) |8x4| ResNet50 | ImageNet|57.76|80.99|x| 8473 | [ckpt]() | [log]() | [json]()|
|tsn_r50_320p_1x1x8_kinetics400_twostream [1: 1]* |x| ResNet50| ImageNet |74.64|91.77| x | x | [ckpt]() | [log]() | [json]()|
|[tsn_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x8_100e_kinetics400_rgb.py) |8| ResNet50 | ImageNet|70.77|89.3|12.2 (8x10 frames)|8344| [ckpt]() | [log]()| [json]()|
|[tsn_r50_video_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_video_1x1x3_100e_kinetics400_rgb.py) |8| ResNet50| ImageNet | x | x |8339| [ckpt]() | [log]()| [json]()|
|[tsn_r50_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb.py) |x| ResNet50 | ImageNet|70.60|89.26|4.3 (25x10 frames)|8344| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb/tsn_r50_1x1x3_100e_kinetics400_rgb_20200614-e508be42.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb/20200614_063526.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb/20200614_063526.log.json)|
|[tsn_r50_1x1x5_50e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x5_50e_kinetics400_rgb.py) |x| ResNet50| ImageNet |68.64|88.19|86.7 (8x1 frames)|7031| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x5_50e_kinetics400_rgb/tsn_r50_1x1x5_50e_kinetics400_rgb_20200608-058a82c3.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x5_50e_kinetics400_rgb/20200608_161221.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x5_50e_kinetics400_rgb/20200608_161221.log.json)|
|[tsn_r50_dense_1x1x5_50e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb.py) |x| ResNet50| ImageNet |68.59|88.31|12.7 (8x10 frames)|7028| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb/tsn_r50_dense_1x1x5_100e_kinetics400_rgb_20200627-a063165f.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb/20200627_105310.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb/20200627_105310.log.json)|
|[tsn_r50_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x8_100e_kinetics400_rgb.py) |x| ResNet50| ImageNet |69.41|88.37|81.6 (8x1 frames)| x | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)|
|[tsn_r50_320p_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb.py) |x| ResNet50| ImageNet |70.91|89.51|10.7 (25x3 frames)| 8344 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_320p_1x1x3_100e_kinetics400_rgb_20200702-cc665e2a.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_f3_kinetics400_shortedge_70.9_89.5.log) | [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/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) |x| ResNet50 | ImageNet|55.70|79.85|x| 8471 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_320p_1x1x3_110e_kinetics400_flow/tsn_r50_320p_1x1x3_110e_kinetics400_flow_20200705-3036bab6.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_320p_1x1x3_110e_kinetics400_flow/tsn_r50_f3_kinetics400_flow_shortedge_55.7_79.9.log) | [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/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| ResNet50 | ImageNet|72.76|90.52| x | x | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/) | [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)|
|[tsn_r50_320p_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb.py) |x| ResNet50| ImageNet |72.41|90.55|11.1 (25x3 frames)| 8344 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb/tsn_r50_320p_1x1x8_100e_kinetics400_rgb_20200702-ef80e3d7.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb/tsn_r50_f8_kinetics400_shortedge_72.4_90.6.log) | [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/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) |x| ResNet50 | ImageNet|57.76|80.99|x| 8473 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_320p_1x1x8_110e_kinetics400_flow/tsn_r50_320p_1x1x8_110e_kinetics400_flow_20200705-1f39486b.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_320p_1x1x8_110e_kinetics400_flow/tsn_r50_f8_kinetics400_flow_shortedge_57.8_81.0.log) | [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/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| ResNet50| ImageNet |74.64|91.77| x | x | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/) | [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)|
|[tsn_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x8_100e_kinetics400_rgb.py) |x| ResNet50 | ImageNet|70.77|89.3|12.2 (8x10 frames)|8344| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)|
|[tsn_r50_video_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_video_1x1x3_100e_kinetics400_rgb.py) |x| ResNet50| ImageNet | x | x |8339| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_video_1x1x3_100e_kinetics400_rgb/tsn_r50_video_1x1x3_100e_kinetics400_rgb_20200622-b1e2040b.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_video_1x1x3_100e_kinetics400_rgb/tsn_r50_video_2d_1x1x3_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).
......@@ -31,27 +31,27 @@ Here, We use [1: 1] to indicate that we combine rgb and flow score with coeffici
|config | gpus| backbone |pretrain| top1 acc| top5 acc | gpu_mem(M) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|[tsn_r50_1x1x8_50e_sthv1_rgb](/configs/recognition/tsn/tsn_r50_1x1x8_50e_sthv1_rgb.py) |8| ResNet50 | ImageNet|18.55|44.80| 10978 | [ckpt]() | [log]()| [json]()|
|[tsn_r50_1x1x16_50e_sthv1_rgb](/configs/recognition/tsn/tsn_r50_1x1x16_50e_sthv1_rgb.py) |8| ResNet50| ImageNet |15.77|39.85| 5691 | [ckpt]() | [log]()| [json]()|
|[tsn_r50_1x1x8_50e_sthv1_rgb](/configs/recognition/tsn/tsn_r50_1x1x8_50e_sthv1_rgb.py) |x| ResNet50 | ImageNet|18.55|44.80| 10978 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x8_50e_sthv1_rgb/tsn_r50_1x1x8_50e_sthv1_rgb_20200618-061b9195.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x8_50e_sthv1_rgb/tsn_sthv1.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x8_50e_sthv1_rgb/tsn_r50_f8_sthv1_18.1_45.0.log.json)|
|[tsn_r50_1x1x16_50e_sthv1_rgb](/configs/recognition/tsn/tsn_r50_1x1x16_50e_sthv1_rgb.py) |x| ResNet50| ImageNet |15.77|39.85| 5691 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x16_50e_sthv1_rgb/tsn_r50_1x1x16_50e_sthv1_rgb_20200614-7e2fe4f1.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x16_50e_sthv1_rgb/20200614_211932.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x16_50e_sthv1_rgb/20200614_211932.log.json)|
### Something-Something V2
|config | gpus| backbone| pretrain | top1 acc| top5 acc | gpu_mem(M) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|[tsn_r50_1x1x8_50e_sthv2_rgb](/configs/recognition/tsn/tsn_r50_1x1x8_50e_sthv2_rgb.py) |8x2| ResNet50| ImageNet |32.41|64.05| 10978 | [ckpt]() | [log]()| [json]()|
|[tsn_r50_1x1x16_50e_sthv2_rgb](/configs/recognition/tsn/tsn_r50_1x1x16_50e_sthv2_rgb.py) |8| ResNet50| ImageNet |22.48|49.08|5698| [ckpt]() | [log]()| [json]()|
|[tsn_r50_1x1x8_50e_sthv2_rgb](/configs/recognition/tsn/tsn_r50_1x1x8_50e_sthv2_rgb.py) |x| ResNet50| ImageNet |32.41|64.05| 10978 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x8_50e_sthv2_rgb/tsn_r50_1x1x8_50e_sthv2_rgb_20200618-096db436.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x8_50e_sthv2_rgb/tsn_sthv2.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x8_50e_sthv2_rgb/tsn_r50_f8_sthv2_32.4_64.1.log.json)|
|[tsn_r50_1x1x16_50e_sthv2_rgb](/configs/recognition/tsn/tsn_r50_1x1x16_50e_sthv2_rgb.py) |x| ResNet50| ImageNet |22.48|49.08|5698| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x16_50e_sthv2_rgb/tsn_r50_1x1x16_50e_sthv2_rgb_20200614-b55c5700.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x16_50e_sthv2_rgb/20200614_203248.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x16_50e_sthv2_rgb/20200614_203248.log.json)|
### Moments in Time
|config | gpus| backbone | pretrain | top1 acc| top5 acc | gpu_mem(M)| ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|[tsn_r50_1x1x6_100e_mit_rgb](/configs/recognition/tsn/tsn_r50_1x1x6_100e_mit_rgb.py) |8x2| ResNet50| ImageNet |26.84|51.6| 8339| [ckpt]() | [log]()| [json]()|
|[tsn_r50_1x1x6_100e_mit_rgb](/configs/recognition/tsn/tsn_r50_1x1x6_100e_mit_rgb.py) |x| ResNet50| ImageNet |26.84|51.6| 8339| [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x6_100e_mit_rgb/tsn_r50_1x1x6_100e_mit_rgb_20200618-d512ab1b.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x6_100e_mit_rgb/tsn_mit.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r50_1x1x6_100e_mit_rgb/tsn_r50_f6_mit_26.8_51.6.log.json)|
### Multi-Moments in Time
|config | gpus| backbone | pretrain | mAP| gpu_mem(M) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|[tsn_r101_1x1x5_50e_mmit_rgb](/configs/recognition/tsn/tsn_r101_1x1x5_50e_mmit_rgb.py) |8x2| ResNet101| ImageNet |61.09| 10467 | [ckpt]() | [log]()| [json]()|
|[tsn_r101_1x1x5_50e_mmit_rgb](/configs/recognition/tsn/tsn_r101_1x1x5_50e_mmit_rgb.py) |x| ResNet101| ImageNet |61.09| 10467 | [ckpt](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r101_1x1x5_50e_mmit_rgb/tsn_r101_1x1x5_50e_mmit_rgb_20200618-642f450d.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r101_1x1x5_50e_mmit_rgb/tsn_mmit.log)| [json](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmaction/mmaction-v1/recognition/tsn/tsn_r101_1x1x5_50e_mmit_rgb/tsn_r101_f6_mmit_61.1.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.
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册