Tensor size mismatch between layers

[JCorpse96]

I pulled this repo to my local machine and trying to run a stackhourglass model in a script that I based off of the Test_img.py script but I'm getting the following error message:
PSMNet\models\stackhourglass.py", line 46, in forward
post = F.relu(self.conv5(out)+pre, inplace=True)
RuntimeError: The size of tensor a (14) must match the size of tensor b (13) at non-singleton dimension 2

Can some one help me with this error?
If more information is needed just ask me and I'll provide it!
Thanks in advanced!

[JiaRenChang]

@JCorpse96
Hi, the input size should be divided evenly by 16.

[Mauric-e]

@JCorpse96
This is not useful, as the test file already contains code that ensures the input size can be divisible by 16 through padding.