https://github.com/apsdehal/face-recognition
Face Recognition project in PyTorch using CNNs
https://github.com/apsdehal/face-recognition
Last synced: about 1 year ago
JSON representation
Face Recognition project in PyTorch using CNNs
- Host: GitHub
- URL: https://github.com/apsdehal/face-recognition
- Owner: apsdehal
- License: mit
- Created: 2014-01-23T14:21:03.000Z (over 12 years ago)
- Default Branch: master
- Last Pushed: 2018-04-11T15:14:13.000Z (about 8 years ago)
- Last Synced: 2024-10-12T02:54:38.772Z (over 1 year ago)
- Language: Python
- Homepage:
- Size: 11.7 KB
- Stars: 39
- Watchers: 10
- Forks: 28
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Face Recognition
Face Recognition using a CNN architecture.
## Dataset
Project uses Yale dataset as a demo, but is extensible to any face recognition dataset. Download Yale Face Database from [here](http://vision.ucsd.edu/content/yale-face-database).
## Running
- Do `pip install -r requirements.txt` to install all deps.
- Get the database as mentioned above. Run `python utils.py ` to create train and val data from `yale_dataset_folder` into `data_folder`.
- Run `giftopng.sh ` to convert all the images inside the subfolders of `` into pngs.
- Run using `python main.py --data ` where `data_folder` contains folders `train` and `val` containing training and validation data respectively.
- Inside `train` and `val` folders, program expects folder for each of the labels and these folder contains samples for these labels.
## TODO
Add picture for the architecture and tune it.
## License
MIT