tinyvision/DAMO-YOLO
DAMO-YOLO is a fast and accurate object detection system based on YOLO with NAS backbones, RepGFPN, and AlignedOTA label assignment.
Not currently ranked — collecting fresh signals.
star history
DAMO-YOLO extends the YOLO framework for object detection by incorporating Neural Architecture Search for backbone design, an efficient Reparameterized Generalized-FPN neck, and AlignedOTA label assignment strategy. The project provides complete training pipelines, distillation techniques for model enhancement, and deployment tools supporting ONNX and TensorRT formats. It includes multiple model sizes from Nano to Large variants optimized for real-time inference.
Frequently asked
- What is tinyvision/DAMO-YOLO?
- DAMO-YOLO is a fast and accurate object detection system based on YOLO with NAS backbones, RepGFPN, and AlignedOTA label assignment.
- Is DAMO-YOLO open source?
- Yes — tinyvision/DAMO-YOLO is open source, released under the Apache-2.0 license.
- What language is DAMO-YOLO written in?
- tinyvision/DAMO-YOLO is primarily written in Python.
- How popular is DAMO-YOLO?
- tinyvision/DAMO-YOLO has 3.2k stars on GitHub.
- Where can I find DAMO-YOLO?
- tinyvision/DAMO-YOLO is on GitHub at https://github.com/tinyvision/DAMO-YOLO.