Holocron: a Deep Learning toolbox for PyTorch

Holocron is meant to bridge the gap between PyTorch and latest research papers. It brings training components that are not available yet in PyTorch with a similar interface.

This project is meant for:

• ⚡ speed: architectures in this repo are picked for both pure performances and minimal latency

• 👩‍🔬 research: train your models easily to SOTA standards

Model zoo

Image classification

• TridentNet from “Scale-Aware Trident Networks for Object Detection”

• SKNet from “Selective Kernel Networks”

• PyConvResNet from “Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition”

• ReXNet from “ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network”

• RepVGG from “RepVGG: Making VGG-style ConvNets Great Again”

Semantic segmentation

• U-Net from “U-Net: Convolutional Networks for Biomedical Image Segmentation”

• U-Net++ from “UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation”

• UNet3+ from “UNet 3+: A Full-Scale Connected UNet For Medical Image Segmentation”

Object detection

• YOLO from “ou Only Look Once: Unified, Real-Time Object Detection”

• YOLOv2 from “YOLO9000: Better, Faster, Stronger”

• YOLOv4 from “YOLOv4: Optimal Speed and Accuracy of Object Detection”