projet-long/README.md
Laurent Fainsin 23295957e6 feat: moar README.md
Former-commit-id: ec05ecb457cdd8c4ef9185b9ca15d527f23e9492 [formerly 2d60ca19027fcf145e4014884f006b4cdc9ae680]
Former-commit-id: 44099b38909857ed940f7d0195875d7e428470ef
2022-09-12 14:52:28 +02:00

113 lines
3.2 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# sphereDetect
sphereDetect is a simple neural network, based on a Mask R-CNN, to detect spherical landmarks for image calibration.
## Built with
- [Python](https://www.python.org/)
### Frameworks
- [PyTorch](https://pytorch.org/)
- [TorchVision](https://pytorch.org/vision/stable/index.html)
- [PyTorch Lightning](https://www.pytorchlightning.ai/)
- [PyTorch Lightning Bolts](https://www.pytorchlightning.ai/bolts)
- [PyTorch Metrics](https://torchmetrics.readthedocs.io/en/stable/)
- [ONNXRuntime](https://onnxruntime.ai/)
### Tools
- [Poetry](https://python-poetry.org/)
- [Docker](https://www.docker.com/)
- [VSCode](https://code.visualstudio.com/)
- [ms-python](https://marketplace.visualstudio.com/items?itemName=ms-python.python)
- [Python Docstring Generator](https://marketplace.visualstudio.com/items?itemName=njpwerner.autodocstring)
- [Conventional Commits](https://marketplace.visualstudio.com/items?itemName=vivaxy.vscode-conventional-commits)
- [Remote container](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers)
- [EditorConfig](https://marketplace.visualstudio.com/items?itemName=EditorConfig.EditorConfig)
- [Docker](https://marketplace.visualstudio.com/items?itemName=ms-azuretools.vscode-docker)
- [Jupyter](https://marketplace.visualstudio.com/items?itemName=ms-toolsai.jupyter)
## Getting started (with docker and vscode)
### Requirements
- [Git](https://git-scm.com/)
- [Docker](https://www.docker.com/)
- [NVIDIA-Docker](https://github.com/NVIDIA/nvidia-docker)
### Installation
Clone the repository:
```bash
git clone git@git.inpt.fr:fainsil/pytorch-reva.git
```
Start VS Code:
```bash
vscode pytorch-reva
```
Install the [Remote Development extension pack](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.vscode-remote-extensionpack). \
Reopen the workspace in [devcontainer mode](https://code.visualstudio.com/docs/remote/containers).
### Usage
Configure [Weights & Biases (local) server](https://docs.wandb.ai/guides/self-hosted/local) at <http://localhost:8080>, and login:
```bash
wandb login --host http://localhost:8080
```
Press `F5` to launch `src/train.py` in debug mode (with breakpoints, slower) \
or press `Ctrl+F5` to launch `src/train.py` in release mode.
## Getting started (without docker)
### Requirements
- [Git](https://git-scm.com/)
- [Poetry](https://python-poetry.org/)
- [Python](https://www.python.org/)
- [Docker](https://www.docker.com/) (if local wandb server used)
### Installation
Clone the repository:
```bash
git clone git@git.inpt.fr:fainsil/pytorch-reva.git
cd pytorch-reva
```
Install the dependencies:
```bash
poetry install --with all
```
### Usage
Activate python environment:
```bash
poetry shell
```
Configure [Weights & Biases (local) server](https://docs.wandb.ai/guides/self-hosted/local), and login:
```bash
wandb server start
wandb login --host http://localhost:8080
```
Start a training:
```bash
python src/train.py
```
## License
Distributed under the [MIT](https://choosealicense.com/licenses/mit/) license. \
See [`LICENSE`](https://git.inpt.fr/fainsil/pytorch-reva/-/blob/master/LICENSE) for more information.
## Contact
Laurent Fainsin _[loʁɑ̃ fɛ̃zɛ̃]_ \
\<[laurent@fainsin.bzh](mailto:laurent@fainsin.bzh)\>