Super fast and high accuracy lightweight anchor-free object detection model. Real-time on mobile devices. NanoDet is a FCOS-style one-stage anchor-free object detection model which using Generalized Focal Loss as classification and regression loss. In NanoDet-Plus, we propose a novel label assignment strategy with a simple assign guidance module (AGM) and a dynamic soft label assigner (DSLA) to solve the optimal label assignment problem in lightweight model training. We also introduce a light feature pyramid called Ghost-PAN to enhance multi-layer feature fusion. These improvements boost previous NanoDet's detection accuracy by 7 mAP on COCO dataset. NanoDet provide multi-backend C++ demo including ncnn, OpenVINO and MNN. There is also an Android demo based on ncnn library. Supports various backends including ncnn, MNN and OpenVINO. Also provide Android demo based on ncnn inference framework.
Features
- Super lightweight
- Model file is only 980KB(INT8) or 1.8MB(FP16)
- Super fast: 97fps(10.23ms) on mobile ARM CPU
- Up to 34.3 mAPval@0.5:0.95 and still realtime on CPU
- Much lower GPU memory cost than other models. Batch-size=80 is available on GTX1060 6G
- Support various backends including ncnn, MNN and OpenVINO. Also provide Android demo based on ncnn inference framework
Project Samples
