BambooKui issues

Repositories
Issues
Comments

Results 4 issues of


                                            BambooKui

yolov5量化后，部署openvino有问题

在使用sample中有关yolov5的例子时，将他改为openvino_int8平台，量化完成后经过推理得到的confidence太低。但使用onnxruntime和yolo的detect却正常。怎么解决？

自定义一个量化器，是自定义一个量化算法，还是自定义一个一个量化的后端平台？

我想在PPQ上实现一些量化算法（QAT和PTQ都有），并将其部署到硬件后端上，应该怎么做？

量化的yolo含有伪量化算子，PPQ有什么办法转为定点模型

Some doubts regarding quantization in academia and industry.

I have some questions. Previously, I quantized some models using torch.fx, and both the size and speed of the models changed. However, I noticed that these tools are not used...