Open source boilerplate for computer vision research. We solve small problems related to project management, experiment management, code styling, and model training so you can get back to research!
git clone https://github.com/pennpolygons/cv-boilerplate.git
cd cv-boilerplate
make init
git clone https://github.com/pennpolygons/cv-boilerplate.git
cd cv-boilerplate
make init-conda
By default training uses: /research/configs/default.yaml
Training outputs:
- Visdom (in browser): localhost:8000
- Output log file, images, data files, hydra logs, Visdom logs:
/outputs
python research/train.py example=regression
python research/train.py mode.train.max_epochs=1 example=regression
python research/train.py example=classification
python research/train.py mode.train.max_epochs=1 example=classification
This project is a collection of principled choices to make CV research easier. We prioritize using tools that minimize researcher engineering work, help keep the codebase uncluttered, and make research easy to distribute and reproduce.