Giters

affinelayer / pix2pix-tensorflow

Tensorflow port of Image-to-Image Translation with Conditional Adversarial Nets https://phillipi.github.io/pix2pix/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About training image size

hammerwy opened this issue · comments

commented

Thank you for your excellent job.
I get some problem when I train the network using my own dataset in image size of 128*128,
ValueError: Dimension 1 in both shapes must be equal, but are 2 and 1 for 'generator/decoder_7/concat' (op: 'ConcatV2') with input shapes: [1,2,2,512], [1,1,1,512], [] and with computed input tensors: input[2] = <3>.
How can I set the parameters to solve the problem ?
thank you for your reply.

commented

Hi, did you solve this problem? I also encountered some dimension issues.

Thanks in advance!