Pytorch-UNet and unet

The two PyTorch U-Net implementations are competitors, offering alternative solutions for biomedical image segmentation, with the Milesial project boasting significantly more stars, suggesting a potentially more mature or widely recognized implementation.

Pytorch-UNet
51
Established
unet
50
Established
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 25/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 24/25
Stars: 11,266
Forks: 2,731
Downloads:
Commits (30d): 0
Language: Python
License: GPL-3.0
Stars: 322
Forks: 124
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: Apache-2.0
Stale 6m No Package No Dependents
Archived Stale 6m No Package No Dependents

About Pytorch-UNet

milesial/Pytorch-UNet

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

Supports mixed precision training (FP16) and automatic gradient scaling for memory efficiency on modern GPUs, plus multiclass segmentation tasks beyond the original Carvana dataset. Includes Weights & Biases integration for real-time training visualization and a pretrained model loadable via torch.hub, with Docker containerization for reproducible environments.

About unet

intel/unet

U-Net Biomedical Image Segmentation

Scores updated daily from GitHub, PyPI, and npm data. How scores work