update readme

open-mmlab · Mar 13, 2023 · ace0809 · ace0809
1 parent f6ea38a
commit ace0809
Show file tree

Hide file tree

Showing 4 changed files with 9 additions and 9 deletions.
diff --git a/configs/recognition/tpn/README.md b/configs/recognition/tpn/README.md
@@ -29,7 +29,7 @@ Visual tempo characterizes the dynamics and the temporal scale of an action. Mod
 
 | frame sampling strategy | resolution | gpus | backbone | pretrain | top1 acc | top5 acc | reference top1 acc | reference top5 acc | testing protocol | inference time(video/s) | gpu_mem(M) |      config       |      ckpt       |      log       |
 | :---------------------: | :--------: | :--: | :------: | :------: | :------: | :------: | :----------------: | :----------------: | :--------------: | :---------------------: | :--------: | :---------------: | :-------------: | :------------: |
-|          1x1x8          | height 100 | 8x6  | ResNet50 |   TSM    |  48.98   |  78.91   |         x          |         x          | 8 clips x 3 crop |            x            |    8828    | [config](/configs/recognition/tpn/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb.py) | [ckpt](https://download.openmmlab.com/mmaction/v1.0/recognition/tpn/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb_20220913-d2f5c300.pth) | [log](https://download.openmmlab.com/mmaction/v1.0/recognition/tpn/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb.log) |
+|          1x1x8          | height 100 | 8x6  | ResNet50 |   TSM    |  51.87   |  79.67   |         x          |         x          | 8 clips x 3 crop |            x            |    8828    | [config](/configs/recognition/tpn/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb.py) | [ckpt](https://download.openmmlab.com/mmaction/v1.0/recognition/tpn/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb_20230221-940a3615.pth) | [log](https://download.openmmlab.com/mmaction/v1.0/recognition/tpn/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb.log) |
 
 :::{note}
 

diff --git a/configs/recognition/tpn/metafile.yml b/configs/recognition/tpn/metafile.yml
@@ -70,4 +70,4 @@ Models:
       Top 5 Accuracy: 78.91
     Task: Action Recognition
   Training Log: https://download.openmmlab.com/mmaction/v1.0/recognition/tpn/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb.log
-  Weights: https://download.openmmlab.com/mmaction/v1.0/recognition/tpn/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb_20220913-d2f5c300.pth
+  Weights: (https://download.openmmlab.com/mmaction/v1.0/recognition/tpn/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb/tpn-tsm_imagenet-pretrained-r50_8xb8-1x1x8-150e_sthv1-rgb_20230221-940a3615.pth
diff --git a/configs/recognition/tsn/README.md b/configs/recognition/tsn/README.md
@@ -32,8 +32,8 @@ Deep convolutional networks have achieved great success for visual recognition i
 
 | frame sampling strategy | scheduler | resolution | gpus | backbone | pretrain | top1 acc | top5 acc |  testing protocol  | FLOPs  | params |              config              |                           ckpt |                            log |
 | :---------------------: | :-------: | :--------: | :--: | :------: | :------: | :------: | :------: | :----------------: | :----: | :----: | :------------------------------: | -----------------------------: | -----------------------------: |
-|          1x1x8          | MultiStep |  224x224   |  8   | ResNet50 | ImageNet |  34.85   |  66.37   | 25 clips x 10 crop | 102.7G | 24.33M | [config](/configs/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb.py) | [ckpt](https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb_20221122-ad2dbb37.pth) | [log](https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb.log) |
-|         1x1x16          | MultiStep |  224x224   |  8   | ResNet50 | ImageNet |  36.55   |  68.00   | 25 clips x 10 crop | 102.7G | 24.33M | [config](/configs/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb.py) | [ckpt](https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20221122-ee13c8e2.pth) | [log](https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb.log) |
+|          1x1x8          | MultiStep |  224x224   |  8   | ResNet50 | ImageNet |  35.51   |  67.09   | 25 clips x 10 crop | 102.7G | 24.33M | [config](/configs/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb.py) | [ckpt](https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb_20230313-06ad7d03.pth) | [log](https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb.log) |
+|         1x1x16          | MultiStep |  224x224   |  8   | ResNet50 | ImageNet |  36.91   |  68.77   | 25 clips x 10 crop | 102.7G | 24.33M | [config](/configs/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb.py) | [ckpt](https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230221-85bcc1c3.pth) | [log](https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb.log) |
 
 ### Using backbones from 3rd-party in TSN
 

diff --git a/configs/recognition/tsn/metafile.yml b/configs/recognition/tsn/metafile.yml
@@ -210,10 +210,10 @@ Models:
     - Dataset: Kinetics-400
       Task: Action Recognition
       Metrics:
-        Top 1 Accuracy: 34.85
-        Top 5 Accuracy: 66.37
+        Top 1 Accuracy: 35.51
+        Top 5 Accuracy: 67.09
     Training Log: https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb.log
-    Weights: https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb_20221122-ad2dbb37.pth
+    Weights: https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x8-50e_sthv2-rgb_20230313-06ad7d03.pth
 
   - Name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb
     Config: configs/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb.py
@@ -233,7 +233,7 @@ Models:
     - Dataset: Kinetics-400
       Task: Action Recognition
       Metrics:
-        Top 1 Accuracy: 36.55
-        Top 5 Accuracy: 68.00
+        Top 1 Accuracy: 36.91
+        Top 5 Accuracy: 68.77
     Training Log: https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb.log
     Weights: https://download.openmmlab.com/mmaction/v1.0/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20221122-ee13c8e2.pth