Find a file
2023-04-05 22:10:29 +02:00
.vscode feat: add instructions to export to onnx 2023-04-05 22:10:29 +02:00
src fix: various typos 2023-04-05 21:06:23 +02:00
.editorconfig feat: checkpoint wandb logging 2022-07-11 15:34:05 +02:00
.gitattributes feat: add .gitattributes 2022-09-02 16:09:18 +02:00
.gitignore fix: github .gitignore 2023-04-02 19:01:30 +02:00
environment.yml refactor!: move files to python modules 2023-04-05 20:11:01 +02:00
LICENSE feat: add LICENSE 2022-09-12 10:59:58 +02:00
pyproject.toml feat: switch from poetry to micromamba 2023-04-01 19:10:27 +02:00
README.md feat: add instructions to export to onnx 2023-04-05 22:10:29 +02:00

Neural sphere detection in images for lighting calibration

Installation

Clone the repository:

git clone https://github.com/Laurent2916/REVA-DETR.git
cd REVA-DETR/

Install and activate the environment:

micromamba install -f environment.yml
micromamba activate qcav

Usage

Everything is managed thanks to Lightning CLI !

Start a training:

python src/main.py fit

Start inference on images:

python src/main.py predict --ckpt_path <path_to_checkpoint>

Quick and dirty way to export to .onnx:

>>> from src.module import DETR
>>> checkpoint = "<path_to_checkpoint>"
>>> model = DETR.load_from_checkpoint(checkpoint)
>>> model.net.save_pretrained("hugginface_checkpoint")
python -m transformers.onnx --model=hugginface_checkpoint onnx_export/

License

Distributed under the MIT license.
See LICENSE for more information.

Contact

Laurent Fainsin [loʁɑ̃ fɛ̃zɛ̃]
<laurent@fainsin.bzh>