参数不匹配问题：RuntimeError: Error(s) in loading state_dict for YoloBody: size mismatch for last_layer0.6。。

最新推荐文章于 2024-09-30 11:03:09 发布

wangcc342425

最新推荐文章于 2024-09-30 11:03:09 发布

阅读量9.6k

点赞数 11

分类专栏： pycharm python 文章标签： python 算法

本文链接：https://blog.csdn.net/weixin_44239195/article/details/107013620

版权

在使用PyTorch训练YOLOv3时遇到RuntimeError，主要表现为加载state_dict时大小不匹配。错误涉及last_layer多个层的weight和bias。问题可能源于模型结构与权重文件不一致，特别是类别数设置错误。解决方案包括检查并修正训练时的类别数，重新训练并替换正确的权重文件。

摘要由CSDN通过智能技术生成

问题描述

题主主要是在pytorch上跑yolov3 时出现如下问题，经过一次次的bug，各种百度，各种调试之后，写下此博客，希望能有所帮助。才疏学浅，欢迎批评指正
出现的错误主要如下
RuntimeError: Error(s) in loading state_dict for YoloBody:
size mismatch for last_layer0.6.weight: copying a param with shape torch.Size(【255, 1024, 1, 1】) from checkpoint, the shape in current model is torch.Size(【18, 1024, 1, 1】).
size mismatch for last_layer0.6.bias: copying a param with shape torch.Size(【255】) from checkpoint, the shape in current model is torch.Size(【18】).
size mismatch for last_layer1.6.weight: copying a param with shape torch.Size(【255, 512, 1, 1】) from checkpoint, the shape in current model is torch.Size(【18, 512, 1, 1】).
size mismatch for last_layer1.6.bias: copying a param with shape torch.Size(【255】) from checkpoint, the shape in current model is torch.Size(【18】).
size mismatch for last_layer2.6.weight: copying a param with