A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

OpenMMLab Pre-training Toolbox and Benchmark

SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation

Implementation of the AAAI-2025 paper "ConDSeg: A General Medical Image Segmentation Framework via Contrast-Driven Feature Enhancement".

Code release for HarDNet-DFUS

PyTorch入门教程，在线阅读地址：https://datawhalechina.github.io/thorough-pytorch/

Codes for MICCAI2021 paper "Shallow Attention Network for Polyp Segmentation"

The source code of IEEE TPAMI 2025 "Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation".

YOLOv12: Attention-Centric Real-Time Object Detectors

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

ICONIP 2024 (IEEE Access 2025)

Application of level set methods

The pytorch implement of DBCTNet

Code for the paper "When Mamba Meets xLSTM: An Efficient and Precise Method with the XLSTM-VMUNet Model for Skin lesion Segmentation"

WIoU implementation for the YOLOv8

The iterative convolution-thresholding method (ICTM)

This is code for our work "Double level set segmentation model based on mutual exclusion of adjacent regions with application to brain MR images".

This repo is code for our paper "Individual tooth segmentation model combining level set approach with object detection by gradient preserved restrictions on rectangle labels"

Pytorch implements yolov4.Good performance, easy to use, fast speed.

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

We elaborate on a Kullback-Leibler divergence-based Fuzzy C-Means (KLDFCM) algorithm by incorporating a tight wavelet frame transform and morphological reconstruction.

Four commonly used operations on the symmetric positive definite manifold