yolox使用笔记

github地址：

GitHub - Megvii-BaseDetection/YOLOX: YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

megegine安装：

pip3 install megengine -f https://megengine.org.cn/whl/mge.html
 

 报错了，torch加载成功，但是加载失败，

state_dict = torch.load(args.ckpt, map_location=torch.device("cpu"))

import megengine as mge
model = build_and_load(args.ckpt, name=args.name)

报错内容：

 A load persistent id instruction was encountered,

A load persistent id instruction was en

文章来源: blog.csdn.net，作者：AI视觉网奇，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/jacke121/article/details/120686660