Common modules, blocks and losses which can be reused in a deep neural netwok specifically for segmentation Please use technical documentation for a reference to API manual
This project has 2 modules
- Losses (losses.py) -> It has all the loss functions defined as python classes
- DiceLoss
- IoULoss
- CrossEntropyLoss2d
- CombinedLoss
- FocalLoss
- Modules (modules.py) -> It has all the commonly used building blocks of an FCN
- DenseBlock
- EncoderBlock
- DecoderBlock
- ClassifierBlock
- GenericBlock
- SDNetEncoderBlock
- SDNetDecoderBlock
You need to have following in order for this library to work as expected
- Python >= 3.5
- Pytorch >= 1.0.0
- Numpy >= 1.14.0
Always use the latest release. Use following command with appropriate version no(v1.0) in this particular case to install. You can find the link for the latest release in the release section of this github repo
pip install https://github.com/shayansiddiqui/nn-common-modules/releases/download/v1.0/nn_common_modules-1.0-py2.py3-none-any.whl
- Shayan Ahmad Siddiqui - shayansiddiqui
- Abhijit Guha Roy - abhi4ssj
Let us know if you face any issues. You are always welcome to report new issues and bugs and also suggest further improvements. And if you like our work hit that start button on top. Enjoy :)