CycleGan训练报错总结：There is no latest_net_G.pth in the program-generated model

最新推荐文章于 2024-07-13 11:57:56 发布

灰太狼241

最新推荐文章于 2024-07-13 11:57:56 发布

阅读量875

点赞数 1

分类专栏：图形融合学习文章标签： pytorch 深度学习 python

本文链接：https://blog.csdn.net/tjnkyqcy/article/details/130791704

版权

图形融合学习专栏收录该内容

3 篇文章 0 订阅

订阅专栏

文章描述了一位用户在使用CycleGan训练模型时遇到的错误，即缺少latest_net_G.pth文件。用户尝试将latest_net_G_A.pth重命名为latest_net_G.pth，但导致新的错误。通过修改base_model.py文件中的代码，特别是将net.load_state_dict()的strict参数设为False，问题最终得到解决，模型成功运行。

摘要由CSDN通过智能技术生成

CycleGan训练报错总结：There is no latest_net_G.pth in the program-generated model

1，All errors are reported as follows：
Traceback (most recent call last):
File “C:/Users/Administrator/Desktop/pytorch-CycleGAN-and-pix2pix-master/test.py”, line 52, in
model.setup(opt) # regular setup: load and print networks; create schedulers
File “C:\Users\Administrator\Desktop\pytorch-CycleGAN-and-pix2pix-master\models\base_model.py”, line 88, in setup
self.load_networks(load_suffix)
File “C:\Users\Administrator\Desktop\pytorch-CycleGAN-and-pix2pix-master\models\base_model.py”, line 192, in load_networks
state_dict = torch.load(load_path, map_location=str(self.device))
File “E:\Anaconda3\envs\pytorch-gpu-Gan\lib\site-packages\torch\serialization.py”, line 594, in load
with _open_file_like(f, ‘rb’) as opened_file:
File “E:\Anaconda3\envs\pytorch-gpu-Gan\lib\site-packages\torch\serialization.py”, line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File “E:\Anaconda3\envs\pytorch-gpu-Gan\lib\site-packages\torch\serialization.py”, line 211, in init
super(_open_file, self).init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: ‘./checkpoints\maps_cyclegan\latest_net_G.pth’

Here is the folder where I generated the model
C:\Users\Administrator\Desktop\pytorch-CycleGAN-and-pix2pix-master\checkpoints\maps_cyclegan：
-latest_net_D_A.pth
-latest_net_D_B.pth
-latest_net_G_A.pth
-latest_net_G_B.pth
There is no latest_net_G.pth in the program-generated model？

修改：latest_net_G_A.pth直接修改为latest_net_G.pth 从A生成B

2，修改后出现如下错误
在这里插入图片描述
参考：http://www.taodudu.cc/news/show-863207.html?action=onClick

经查找后，在base_model.py文件中199行

196 # patch InstanceNorm checkpoints prior to 0.4
197  for key in list(state_dict.keys()):  # need to copy keys here because we mutate in loop
198  self.__patch_instance_norm_state_dict(state_dict, net, key.split('.'))
199  net.load_state_dict(state_dict,strict=False)  #qcy 添加了strict=False