SOTA 3D Medical Segmentation framework (UNET++, TransUNET , SwimTransUNET) in TensorFlow. Fully TPU-optimized with a 3-stage OHEM pipeline for the Medical Segmentation Decathlon (MSD).
-
Updated
Jan 13, 2026 - Python
SOTA 3D Medical Segmentation framework (UNET++, TransUNET , SwimTransUNET) in TensorFlow. Fully TPU-optimized with a 3-stage OHEM pipeline for the Medical Segmentation Decathlon (MSD).
基于 PyTorch 的皮肤病灶分割实验框架,支持 U-Net 系列、Kaggle GPU 训练、评估、可视化与 Gradio。 / Reproducible PyTorch framework for skin lesion segmentation with U-Net models, Kaggle GPU training, evaluation, visualization, and Gradio.
Add a description, image, and links to the unet-plus-plus topic page so that developers can more easily learn about it.
To associate your repository with the unet-plus-plus topic, visit your repo's landing page and select "manage topics."