zhanghang1989/ResNeSt
ResNeSt is a PyTorch implementation of a ResNet variant with split-attention mechanisms used as a backbone for computer vision tasks.
Not currently ranked — collecting fresh signals.
star history
ResNeSt provides a PyTorch implementation of Split-Attention Networks, a ResNet architecture variant that introduces channel-attention within residual blocks. The model serves as a backbone for various computer vision tasks including object detection, instance segmentation, semantic segmentation, and panoptic segmentation. It includes integration with Detectron2 and benchmarks on COCO and ADE20K datasets.
Frequently asked
- What is zhanghang1989/ResNeSt?
- ResNeSt is a PyTorch implementation of a ResNet variant with split-attention mechanisms used as a backbone for computer vision tasks.
- Is ResNeSt open source?
- Yes — zhanghang1989/ResNeSt is open source, released under the Apache-2.0 license.
- What language is ResNeSt written in?
- zhanghang1989/ResNeSt is primarily written in Python.
- How popular is ResNeSt?
- zhanghang1989/ResNeSt has 3.3k stars on GitHub.
- Where can I find ResNeSt?
- zhanghang1989/ResNeSt is on GitHub at https://github.com/zhanghang1989/ResNeSt.