search

enazoe / yolo-tensorrt

TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.
MIT License
1.19k stars 315 forks source link

int8 is error #96

Open zhangzhixiangah opened 3 years ago

zhangzhixiangah commented 3 years ago

hi,my int8 quantification is error

terminate called after throwing an instance of 'std::out_of_range' what(): _Map_base::at Aborted (core dumped)

ZhenshengLee commented 3 years ago

I have the same issue, any solution?

enazoe commented 3 years ago

trim spaces at https://github.com/enazoe/yolo-tensorrt/blob/master/configs/yolov5-4.0/yolov5l.cfg#L3-L6 or remove the blank line

Lenan22 commented 1 year ago

hi,my int8 quantification is error

terminate called after throwing an instance of 'std::out_of_range' what(): _Map_base::at Aborted (core dumped)

Please refer to our open source quantization tool ppq, the quantization effect is better than the calibration of tensorrt, if you encounter issues, we can help you solve them. https://github.com/openppl-public/ppq/blob/master/md_doc/deploy_trt_by_OnnxParser.md

Lenan22 commented 1 year ago

I have the same issue, any solution?

Please refer to our open source quantization tool ppq, the quantization effect is better than the calibration of tensorrt, if you encounter issues, we can help you solve them. https://github.com/openppl-public/ppq/blob/master/md_doc/deploy_trt_by_OnnxParser.md