Closed FBEMPSS closed 2 years ago
I meet this error also, have you solve this problem?
I also met the same problem. Then it was solved by reinstalling a different version of Pytorch. I’m not sure, may be you can check your Pytorch version, especially the CUDA .
Since the older instance norm uses batch norm as the backend, there are maybe some issues when the batch size is 1.
I also met the same problem. Then it was solved by reinstalling a different version of Pytorch. I’m not sure, may be you can check your Pytorch version, especially the CUDA .
May I ask u about your server environment configuration? I also encountered this problem, so sad
I also met the same problem. Then it was solved by reinstalling a different version of Pytorch. I’m not sure, may be you can check your Pytorch version, especially the CUDA .
May I ask u about your server environment configuration? I also encountered this problem, so sad
Are u solve this problem? I also confused about it, so sad.
I also met the same problem. Then it was solved by reinstalling a different version of Pytorch. I’m not sure, may be you can check your Pytorch version, especially the CUDA .
May I ask u about your server environment configuration? I also encountered this problem, so sad
Are u solve this problem? I also confused about it, so sad.
Use torch 1.4 & python 3.6 help me solve this problem
when input image size is 64 in style encoder,it will be transformed to a tensor which size is (1, 165, 1 ,1) and it will be fed into residual black , which has a conv(kernel = 3) and generate an error.