https://github.com/vra/action-recognition-using-3d-resnet
Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.
https://github.com/vra/action-recognition-using-3d-resnet
3d-resnet action-recognition cnn deep-learning extract-features hmdb51 ucf101
Last synced: about 1 year ago
JSON representation
Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.
- Host: GitHub
- URL: https://github.com/vra/action-recognition-using-3d-resnet
- Owner: vra
- Created: 2017-11-25T15:57:42.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2018-11-25T13:13:03.000Z (over 7 years ago)
- Last Synced: 2025-03-26T02:51:14.527Z (about 1 year ago)
- Topics: 3d-resnet, action-recognition, cnn, deep-learning, extract-features, hmdb51, ucf101
- Language: Python
- Homepage:
- Size: 166 KB
- Stars: 41
- Watchers: 2
- Forks: 12
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# action-recognition-using-3d-resnet
Use [3D ResNet](https://github.com/kenshohara/video-classification-3d-cnn-pytorch) to extract features of UCF101 and HMDB51 and then classify them.
# how to use
1. Clone this repo:
```bash
git clone https://github.com/vra/action-recognition-using-3d-resnet.git
```
2. Download [3D ResNet](https://github.com/kenshohara/video-classification-3d-cnn-pytorch)
3. Download its pretrained [models](https://github.com/kenshohara/3D-ResNets-PyTorch/releases), put these models to this repo's `data/models/`
4. run the script under `scripts` under to extract 3D resnet features of UCF101 and HMDB51:
```bash
bash scripts/extract_resnet_3d_features.sh /path/to/video-classification/3d-cnn-pytorch ucf101 /path/to/ucf101/videos
bash scripts/extract_resnet_3d_features.sh /path/to/video-classification/3d-cnn-pytorch hmdb51 /path/to/hmdb51/videos
```
Also, you can download my extracted features of ucf101 and hmdb51 at [here](https://drive.google.com/open?id=12BM8ibl5oFziM-59JqXmsqMjtx7_qthZ) and [here](https://drive.google.com/open?id=178U8N6dPBfpaHYMxdOCCWpLa4hl6kFjk). **Remember to put the first one to `data/jsons/ucf101` before you download the second one, otherwise the first one will be convered.**
5. Run `main.py` to classify extracted 3D resnet features:
```bash
python main.py -dataset hmdb51
```
Results:
strategy | dataset | accuracy
-------- | ------- | -------
mean | ucf101 | 0.8487
max | ucf101 | 0.8667
mean | hmdb51 | 0.5425
max | hmdb51 | 0.5399