Metadata-Version: 2.1
Name: cnn_framework
Version: 0.0.3
Summary: CNN framework
Home-page: https://https://github.com/15bonte/cnn_framework
Author: Thomas Bonte
Author-email: thomas.bonte@mines-paristech.fr
Project-URL: Bug Tracker, https://https://github.com/15bonte/cnn_framework/issues
Classifier: Programming Language :: Python :: 3.9
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch>=1.12.1
Requires-Dist: scikit-image>=0.19.3
Requires-Dist: matplotlib
Requires-Dist: scikit-learn>=1.2.2
Requires-Dist: pint>=0.19.2
Requires-Dist: torchvision>=0.13.1
Requires-Dist: albumentations==1.3.0
Requires-Dist: torchmetrics>=0.11.4
Requires-Dist: big-fish>=0.6.2
Requires-Dist: pillow>=9.2.0
Requires-Dist: segmentation-models-pytorch>=0.3.0
Requires-Dist: GitPython==3.1.27
Requires-Dist: protobuf==3.20.*
Requires-Dist: tensorboard==2.8.0

# CNN framework

Run CNN models for classification, regression, segmentation, VAE, contrastive learning with any data set.

## Installation

First, create a dedicated conda environment using Python 3.9

```bash
conda create -n cnn_framework python=3.9
conda activate cnn_framework
```

To install the latest github version of this library run the following using pip

```bash
pip install git+https://github.com/15bonte/cnn_framework
```

or alternatively you can clone the github repository

```bash
git clone https://github.com/15bonte/cnn_framework.git
cd cnn_framework
pip install -e .
```

If you want to run jupyter tutorials, you also need to install ipykernel

```bash
pip install ipykernel
```

If you want to work with VAE, you must also install [Pythae](https://github.com/clementchadebec/benchmark_VAE/tree/main) and [WandB](https://wandb.ai/home), which is not the case by default.

```bash
pip install pythae
```

```bash
pip install wandb
```
