使用量化后的模型进行推理报错Delete Weight Dequant Linear Op Pass is not supported for per-channel quantization

PaddlePaddle / PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

Apache License 2.0

38.99k stars 7.32k forks source link

使用量化后的模型进行推理报错Delete Weight Dequant Linear Op Pass is not supported for per-channel quantization #11990

Closed Capricorn-18 closed 2 weeks ago

Capricorn-18 commented 3 weeks ago

根据官方的文档对训练好的模型进行量化之后得到的pdparams文件可以在infer_det.py和infer_rec.py运行，但是使用slim的export_model.py将量化的模型转成pdiparams文件之后，运行predict_det.py和predict_rec.py文件就报上面的问题了，想问一下这是为什么呢？

TingquanGao commented 3 weeks ago

pdiparams文件是静态图推理模型文件。具体是什么报错，可以贴一下报错信息吗？以及使用的命令是啥？

Sunting78 commented 2 weeks ago

您好，超过一周未回复的问题将关闭，如未解决可以open或者重新提issue。