https://github.com/facebookarchive/c3d
C3D is a modified version of BVLC caffe to support 3D ConvNets.
https://github.com/facebookarchive/c3d
Last synced: 4 months ago
JSON representation
C3D is a modified version of BVLC caffe to support 3D ConvNets.
- Host: GitHub
- URL: https://github.com/facebookarchive/c3d
- Owner: facebookarchive
- License: other
- Archived: true
- Created: 2015-04-10T04:48:11.000Z (almost 11 years ago)
- Default Branch: master
- Last Pushed: 2019-07-31T22:24:07.000Z (over 6 years ago)
- Last Synced: 2024-04-10T05:26:10.725Z (almost 2 years ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 27.9 MB
- Stars: 1,159
- Watchers: 54
- Forks: 503
- Open Issues: 76
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
Awesome Lists containing this project
README
# C3D
C3D is a modified version of BVLC caffe to support 3D convolution and pooling.
The main supporting features include:
- Training or fine-tuning 3D ConvNets.
- Extracting video features with pre-trained C3D models.
For more information about C3D, please refer to the [C3D project website](http://vlg.cs.dartmouth.edu/c3d).
For general questions about Caffe, please refer to the [BVLC project website](http://caffe.berkeleyvision.org) for all documentation.
## Updates
If you are about to start or just started your project, we would like to recommend you to use our C3D model in caffe2 [link](https://github.com/facebookresearch/R2Plus1D), which has better documentations and longer-term support. Additionally, we provide many more pre-trained models including R2D, R3D, MCx, rMCx, R(2+1)D, and more to come!
## License
C3D is licensed under the Creative Commons Attribution-NonCommercial 3.0, as found in the LICENSE file.