@@ -41,16 +46,28 @@ It is a part of the [OpenMMLab project](https://github.com/open-mmlab) developed
- For temporal action localization, we implement BSN, BMN.
+- **Well tested and documented**
+
+ We provide detailed documentation and API reference, as well as unittests.
+
## License
This project is released under the [Apache 2.0 license](LICENSE).
## Benchmark and Model Zoo
-Benchmark with other repos are available on [benchmark.md](docs/benchmark.md).
+MMAction2 supports various models and is more efficient in training.
+We compare with other popular codebases and the results are shown as below.
-Results and models are available in the *README.md* of each method's config directory.
-A summary can be found in the [**model zoo**](https://mmaction2.readthedocs.io/en/latest/modelzoo.html) page.
+| Model | MMAction2 (s/iter) | MMAction (s/iter) | Temporal-Shift-Module (s/iter) | PySlowFast (s/iter) |
+| :--- | :---------------: | :--------------------: | :----------------------------: | :-----------------: |
+| [TSN](/configs/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb.py) | **0.29** | 0.36 | 0.45 | x |
+| [I3D (setting1)](/configs/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb.py) | **0.45** | 0.58 | x | x |
+| [I3D (setting2)](/configs/recognition/i3d/i3d_r50_8x8x1_100e_kinetics400_rgb.py) | **0.32** | x | x | 0.56 |
+| [TSM](/configs/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb.py) | **0.30** | x | 0.38 | x |
+| [Slowonly](/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb.py) | **0.30** | x | x | 1.03 |
+| [Slowfast](/configs/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py) | **0.80** | x | x | 1.40 |
+| [R(2+1)D](/configs/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb.py) | **0.48** | x | x | x |
Supported methods for action recognition:
- [x] [TSN](configs/recognition/tsn/README.md)
@@ -64,6 +81,9 @@ Supported methods for action localization:
- [x] [BMN](configs/localization/bmn/README.md)
- [x] [BSN](configs/localization/bsn/README.md)
+Results and models are available in the *README.md* of each method's config directory.
+A summary can be found in the [**model zoo**](https://mmaction2.readthedocs.io/en/latest/modelzoo.html) page.
+
## Installation
Please refer to [install.md](docs/install.md) for installation.
diff --git a/docs/benchmark.md b/docs/benchmark.md
index 7e1f67e7e38b1a4bbe98813cc7c562f1d9f2a73f..04d354229a4f6750f561b860fc90a3c16d4ebd8d 100644
--- a/docs/benchmark.md
+++ b/docs/benchmark.md
@@ -23,15 +23,13 @@ The training speed is measure with s/iter. The lower, the better.
| Model | MMAction2 (s/iter) | MMAction (s/iter) | Temporal-Shift-Module (s/iter) | PySlowFast (s/iter) |
| :--- | :---------------: | :--------------------: | :----------------------------: | :-----------------: |
-| TSN ([tsn_r50_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb.py)) | **0.29** | 0.36 | 0.45 | x |
-| I3D ([i3d_r50_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb.py)) | **0.45** | 0.58 | x | x |
-| I3D ([i3d_r50_8x8x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_8x8x1_100e_kinetics400_rgb.py)) | **0.32** | x | x | 0.56 |
-| TSM ([tsm_r50_1x1x8_50e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb.py)) | **0.30** | x | 0.38 | x |
-| Slowonly ([slowonly_r50_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb.py)) | **0.30** | x | x | 1.03 |
-| Slowonly ([slowonly_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb.py)) | **0.50** | x | x | 1.29 |
-| Slowfast ([slowfast_r50_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py)) | **0.80** | x | x | 1.40 |
-| Slowfast ([slowfast_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py)) | **1.05** | x | x | 1.41 |
-| R(2+1)D ([r2plus1d_r34_8x8x1_180e_kinetics400_rgb](/configs/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb.py)) | **0.48** | x | x | x |
+| [TSN](/configs/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb.py) | **0.29** | 0.36 | 0.45 | x |
+| [I3D (setting1)](/configs/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb.py) | **0.45** | 0.58 | x | x |
+| [I3D (setting2)](/configs/recognition/i3d/i3d_r50_8x8x1_100e_kinetics400_rgb.py) | **0.32** | x | x | 0.56 |
+| [TSM](/configs/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb.py) | **0.30** | x | 0.38 | x |
+| [Slowonly](/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb.py) | **0.30** | x | x | 1.03 |
+| [Slowfast](/configs/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py) | **0.80** | x | x | 1.40 |
+| [R(2+1)D](/configs/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb.py) | **0.48** | x | x | x |
## Localizers
+
+
-## Introduction
-
-The master branch works with **PyTorch 1.3+**. Documentation: https://mmaction2.readthedocs.io/
+Documentation: https://mmaction2.readthedocs.io/.
+
+## Introduction
MMAction2 is an open-source toolbox for action understanding based on PyTorch.
-It is a part of the [OpenMMLab project](https://github.com/open-mmlab) developed by [Multimedia Laboratory, CUHK](http://mmlab.ie.cuhk.edu.hk/).
+It is a part of the [OpenMMLab](http://openmmlab.org/) project.
+
+The master branch works with **PyTorch 1.3+**.