sssssshf / Holocron

PyTorch implementations of recent Computer Vision tricks (ReXNet, RepVGG, Unet3p, YOLOv4, CIoU loss, AdaBelief)

Holocron

Implementations of recent Deep Learning tricks in Computer Vision, easily paired up with your favorite framework and model zoo.

Holocrons were information-storage datacron devices used by both the Jedi Order and the Sith that contained ancient lessons or valuable information in holographic form.

Source: Wookieepedia

Note: support of activation mapper and model summary has been dropped and outsourced to independent packages (torch-cam & torch-scan) to clarify project scope.

Quick Tour

PyTorch layers for every need

• Activation: SiLU/Swish, Mish, HardMish, NLReLU, FReLU
• Loss: Focal Loss, MultiLabelCrossEntropy, LabelSmoothingCrossEntropy, MixupLoss, ClassBalancedWrapper, ComplementCrossEntropy, MutualChannelLoss
• Convolutions: NormConv2d, Add2d, SlimConv2d, PyConv2d
• Regularization: DropBlock
• Pooling: BlurPool2d, SPP, ZPool
• Attention: SAM, LambdaLayer, TripletAttention

Models for vision tasks

• Classification: Res2Net (based on the great implementation from Ross Wightman), Darknet-24, Darknet-19, Darknet-53, CSPDarknet-53, ResNet, ResNeXt, TridentNet, PyConvResNet, ReXNet, SKNet, RepVGG.
• Detection: YOLOv1, YOLOv2, YOLOv4
• Segmentation: U-Net, UNet++, UNet3+

Vision-related operations

• boxes: Distance-IoU & Complete-IoU losses

Trying something else than Adam

• Optimizer: LARS, Lamb, RAdam, TAdam, AdamP, AdaBelief, and customized versions (RaLars)
• Optimizer wrapper: Lookahead, Scout (experimental)

Setup

Python 3.6 (or higher) and pip/conda are required to install Holocron.

Stable release

You can install the last stable release of the package using pypi as follows:

pip install pylocron

or using conda:

conda install -c frgfm pylocron

Developer installation

Alternatively, if you wish to use the latest features of the project that haven't made their way to a release yet, you can install the package from source:

git clone https://github.com/frgfm/Holocron.git
pip install -e Holocron/.

What else

Documentation

The full package documentation is available here for detailed specifications.

Reference scripts

Reference scripts are provided to train your models using holocron on famous public datasets. Those scripts currently support the following vision tasks:

• Image classification
• Object detection
• Semantic segmentation

Citation

If you wish to cite this project, feel free to use this BibTeX reference:

@misc{holocron2019,
    title={Holocron},
    author={François-Guillaume Fernandez},
    year={2019},
    month={August},
    publisher = {GitHub},
    howpublished = {\url{https://github.com/frgfm/Holocron}}
}

Contributing

Any sort of contribution is greatly appreciated!

You can find a short guide in CONTRIBUTING to help grow this project!

License

Distributed under the Apache 2.0 License. See LICENSE for more information.