yu-changqian/TorchSeg
PyTorch-based modular reference implementation for semantic segmentation models with distributed training and multi-GPU support.
Not currently ranked — collecting fresh signals.
star history
TorchSeg provides a fast, modular framework for implementing and training semantic segmentation algorithms in PyTorch. It includes pre-trained models (ResNet18/50/101) and supports popular segmentation architectures such as FCN, DFN, BiSeNet, PSPNet, and PSANet. The project offers distributed training capabilities for multi-GPU setups and benchmarks on datasets including PASCAL VOC 2012, Cityscapes, ADE20K, and CamVid.
Frequently asked
- What is yu-changqian/TorchSeg?
- PyTorch-based modular reference implementation for semantic segmentation models with distributed training and multi-GPU support.
- Is TorchSeg open source?
- Yes — yu-changqian/TorchSeg is open source, released under the MIT license.
- What language is TorchSeg written in?
- yu-changqian/TorchSeg is primarily written in Python.
- How popular is TorchSeg?
- yu-changqian/TorchSeg has 1.4k stars on GitHub.
- Where can I find TorchSeg?
- yu-changqian/TorchSeg is on GitHub at https://github.com/yu-changqian/TorchSeg.