Skip to content

Conversation

@askorelas
Copy link

Came across a bug when using smaller picture sizes than 256. The function load_train_data method wasn't given the picture shape that the network was built with, which resulted in incompatible tensor shapes.

@Deeplearning20
Copy link

@askorelas Hello, I changed my picture to 256*256. But there is a problem, how did you solve it?Thanks
very much!
ValueError: Cannot feed value of shape (0,) for Tensor 'real_A_and_B_images:0', which has shape '(?, 256, 256, 6)'
image

@star0w
Copy link

star0w commented Nov 28, 2020

@askorelas Hello, I changed my picture to 256*256. But there is a problem, how did you solve it?Thanks
very much!
ValueError: Cannot feed value of shape (0,) for Tensor 'real_A_and_B_images:0', which has shape '(?, 256, 256, 6)'
image

hello! have u solved this problem?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants