torch.load()加载模型，提示xxx.pt is a zip archive(did you mean to use torch.jit.load()?)

本文转载自查看原文 2021-04-02 10:00 1054 pytorch

参考链接

https://blog.csdn.net/irober/article/details/115144522?utm_medium=distribute.pc_relevant.none-task-blog-baidujs_title-0&spm=1001.2101.3001.4242

torch版本问题

import torch
state_dict = torch.load("./model_00050.pt")#加载原来的模型  在torch=1.6时加载
torch.save(state_dict, "./00050.pt", _use_new_zipfile_serialization=False)#不是zip

再加载save后的模型即可

免责声明！

本站转载的文章为个人学习借鉴使用，本站对版权不负任何法律责任。如果侵犯了您的隐私权益，请联系本站邮箱yoyou2525@163.com删除。

猜您在找 PyTorch错误解决：XXX is a zip archive(did you mean to use torch.jit.load()?) Mapstruct使用时报Unknown property xxx in result type xxx. Did you mean null? torch.load CUDA ERROR: out of memory Pytorch中torch.load()加载预训练权重报错 Symfony 3.4 安装报错 Warning: "continue" targeting switch is equivalent to "break". Did you mean to use "continue 2"? Command 'vcs' not found, did you mean npm run dev提示npm WARN Local package.json exists, but node_modules missing, did you mean to install? nvidia jetson xavier NX编译darknet时提示opencv错误， error: ‘IplImage’ does not name a type; did you mean ‘image’? Unknown type name 'class'; did you mean 'Class'? 问题的解决 django Did you forget to register or load this tag?