hd201708010401
hd201708010401
> 我在运行的时候遇到了Tensor尺寸不匹配的问题，楼主有遇到这个情况吗 `copying a param with shape torch.Size([30]) from checkpoint, the shape in current model is torch.Size([27]).` 显示的是预训练模型与当前模型参数尺度不一致 > 我在运行的时候遇到了Tensor尺寸不匹配的问题，楼主有遇到这个情况吗 `copying a param with shape torch.Size([30]) from checkpoint, the shape...
when I use facdes datasets to train the model ,I can get the translated images, the translated images are same with the input images
邮件已经收到，谢谢。I have received your email. Thank you for your letter.
@JunlinHan Can you provide the pre-training model of SimDCL trained facades? My training model still has the phenomenon of model collapse, which cannot reproduce the effect in the article.
邮件已经收到，谢谢。I have received your email. Thank you for your letter.
Testing btoa requires retraining the network?
邮件已经收到，谢谢。I have received your email. Thank you for your letter.
邮件已经收到，谢谢。I have received your email. Thank you for your letter.
I met the same problem
邮件已经收到，谢谢。I have received your email. Thank you for your letter.