AXERA-TECH / yolov5-qatLinks
Try to export the ONNX QDQ model that conforms to the AXERA NPU quantization specification. Currently, only w8a8 is supported.
☆10Updated 8 months ago
Alternatives and similar repositories for yolov5-qat
Users that are interested in yolov5-qat are comparing it to the libraries listed below
Sorting:
- An onnx-based quantitation tool.☆71Updated last year
- ☆22Updated last year
- Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX. And Export the ONNX model for AXera's NPU☆12Updated last week
- A set of examples around MegEngine☆31Updated last year
- DETR tensor去除推理过程无用辅助头+fp16部署再次 加速+解决转tensorrt 输出全为0问题的新方法。☆12Updated last year
- ☆20Updated last year
- 这是一个使用opencv读取视频并使用socket进行传输视频画面的脚本文件,相较于调用ffmpeg传输节约了90%的数据量☆11Updated last year
- ☆15Updated last year
- ☆19Updated 2 years ago
- Llama3 Streaming Chat Sample☆22Updated last year
- ☆24Updated last year
- ☆12Updated last year
- Quantize yolov5 using pytorch_quantization.🚀🚀🚀☆14Updated last year
- a Android demo of depth_anything_v1 and depth_anything_v2☆59Updated 11 months ago
- Speed up image preprocess with cuda when handle image or tensorrt inference☆68Updated 3 weeks ago
- ☆10Updated 10 months ago
- 搜藏的希望的代码片段☆13Updated last year
- ffmpeg+cuvid+tensorrt+multicamera☆12Updated 5 months ago
- This is 8-bit quantization sample for yolov5. Both PTQ, QAT and Partial Quantization have been implemented, and present the results based…☆102Updated 2 years ago
- A tool convert TensorRT engine/plan to a fake onnx☆39Updated 2 years ago
- Based of paper "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference"☆64Updated 4 years ago
- Offline Quantization Tools for Deploy.☆128Updated last year
- the C++ version of solov2 with ncnn☆76Updated 3 years ago
- SAM and lama inpaint,包含QT的GUI交互界面,实现了交互式可实时显示结果的画点、画框进行SAM,然后通过进行Inpaint,具体操作看readme里的视频。☆47Updated last year
- PyTorch Quantization Aware Training(QAT,量化感知训练)☆30Updated last year
- 用pytorch训练ssd,相比原版pytorch-ssd改动了不少☆11Updated 2 years ago
- trt-hackathon-2022 三等奖方案☆10Updated 2 years ago
- Quantize yolov7 using pytorch_quantization.🚀🚀🚀☆10Updated last year
- NanoTrack(@HonglinChu), C++ TensorRT deployment. MAX 250 FPS!☆24Updated last year
- HunyuanDiT with TensorRT and libtorch☆17Updated last year