Res2Net/Res2Net-PretrainedModels
Multi-scale CNN backbone architecture for computer vision tasks, implemented in PyTorch with ImageNet pretrained weights.
Not currently ranked — collecting fresh signals.
star history
This repository provides the official PyTorch implementation of Res2Net, a multi-scale feature extraction backbone for convolutional neural networks published at IEEE TPAMI. The architecture introduces a hierarchical residual-like connection pattern within a single residual block to capture features at multiple scales. Pretrained Res2Net_v1b models are provided, achieving strong performance on ImageNet classification and serving as effective backbones for downstream tasks including object detection, semantic segmentation, and panoptic segmentation.
Frequently asked
- What is Res2Net/Res2Net-PretrainedModels?
- Multi-scale CNN backbone architecture for computer vision tasks, implemented in PyTorch with ImageNet pretrained weights.
- Is Res2Net-PretrainedModels open source?
- Yes — Res2Net/Res2Net-PretrainedModels is an open-source project tracked on heatdrop.
- What language is Res2Net-PretrainedModels written in?
- Res2Net/Res2Net-PretrainedModels is primarily written in Python.
- How popular is Res2Net-PretrainedModels?
- Res2Net/Res2Net-PretrainedModels has 1.1k stars on GitHub.
- Where can I find Res2Net-PretrainedModels?
- Res2Net/Res2Net-PretrainedModels is on GitHub at https://github.com/Res2Net/Res2Net-PretrainedModels.