yhenon/pytorch-retinanet
PyTorch implementation of RetinaNet object detection model with ResNet backbone.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of RetinaNet as described in the Focal Loss paper by Lin et al. It is designed for dense object detection tasks and supports training on COCO format datasets or custom CSV-annotated datasets. The model achieves competitive mAP scores (33.5% at 600px with ResNet-50) and includes pre-trained weights for download.
Frequently asked
- What is yhenon/pytorch-retinanet?
- PyTorch implementation of RetinaNet object detection model with ResNet backbone.
- Is pytorch-retinanet open source?
- Yes — yhenon/pytorch-retinanet is open source, released under the Apache-2.0 license.
- What language is pytorch-retinanet written in?
- yhenon/pytorch-retinanet is primarily written in Python.
- How popular is pytorch-retinanet?
- yhenon/pytorch-retinanet has 2.2k stars on GitHub.
- Where can I find pytorch-retinanet?
- yhenon/pytorch-retinanet is on GitHub at https://github.com/yhenon/pytorch-retinanet.