Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Video classification tools using 3D ResNet
| Date | Stars |
|---|---|
| 2026-07-24 | 1128 |
| 2026-07-25 | 1128 |
| 2026-07-28 | 1128 |
| 2026-07-30 | 1128 |
| 2026-08-06 | 1128 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Video Classification Using 3D ResNet
This is a pytorch code for video (action) classification using 3D ResNet trained by [this code](https://github.com/kenshohara/3D-ResNets-PyTorch).
The 3D ResNet is trained on the Kinetics dataset, which includes 400 action classes.
This code uses videos as inputs and outputs class names and predicted class scores for each 16 frames in the score mode.
In the feature mode, this code outputs features of 512 dims (after global average pooling) for each 16 frames.
**Torch (Lua) version of this code is available [here](https://github.com/kenshohara/video-classification-3d-cnn).**
## Requirements
* [PyTorch](http://pytorch.org/)
```
conda install pytorch torchvision cuda80 -c soumith
```
* FFmpeg, FFprobe
```
wget http://johnvansickle.com/ffmpeg/releases/ffmpeg-release-64bit-static.tar.xz
tar xvf ffmpeg-release-64bit-static.tar.xz
cd ./ffmpeg-3.3.3-64bit-static/; sudo cp ffmpeg ffprobe /usr/local/bin;
```
* Python 3
## Preparation
* Download this code.
* Download the [pretrained model](https://drive.google.com/drive/folders/1zvl89AgFAApbH0At-gMuZSeQB_LpNP-M?usp=sharing).
* ResNeXt-101 achieved the best performance in our experiments. (See [paper](https://arxiv.org/abs/1711.09577) in details.)
## Usage
Assume input video files are located in ```./videos```.
To calculate class scores for each 16 frames, use ```--mode score```.
```
python main.py --input ./input --video_root ./videos --output ./output.json --model ./resnet-34-kinetics.pth --mode score
```
To visualize the classification results, use ```generate_result_video/generate_result_video.py```.
To calculate video features for each 16 frames, use ```--mode feature```.
```
python main.py --input ./input --video_root ./videos --output ./output.json --model ./resnet-34-kinetics.pth --mode feature
```
## Citation
If you use this code, please cite the following:
```
@article{hara3dcnns,
author={Kensho Hara and Hirokatsu Kataoka and Yutaka Satoh},
title={Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?},
journal={arXiv preprint},
volume={arXiv:1711.09577},
year={2017},
}
```
Excerpt of 2,144 characters
Read on GitHub
23
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3d6b4b05f5ff39a9, topic:deep-learning, topic:pytorch
matched fp:3d6b4b05f5ff39a9, topic:computer-vision