Hello, I have a problem that the calculated output size is too small (512*1*0）when I train the model, is there anyone who have successfully run the pretrained train_PBAFN_stage1_fs.sh model could give me some suggestions?
wyf-gh opened this issue · comments
)
I met the same problem too
please check your input size, the PyTorch version you are using, etc.
The PyTorch version I used is 1.10.0 suitable for CUDA11.1, I don't know which input size to check.
If you met the same problem, have you found the solution? @Dylonsword
I met the same problem too ，have you found the solution@SenHe @Dylonsword @wyf-gh
please refer to a previous issue.
You could simply change the ceil mode of maxpool layer from last sequential layer of VGG networks to True if you are running on different pytorch version from author's.
You could simply change the ceil mode of maxpool layer from last sequential layer of VGG networks to True if you are running on different pytorch version from author's.
Thanks!
Thank you ! @JacksonCakes
I have met the same issue，then I process the picture to the 192*256 ,the issue has been solved
@wang674 @Hanjunzhe @Dylonsword Did u complete your project?
I have met the same issue，then I process the picture to the 192*256 ,the issue has been solved
could you tell me how to process the picture?thx!!!!!