GlobalLocalImageCompletion_TF icon indicating copy to clipboard operation
GlobalLocalImageCompletion_TF copied to clipboard

Test script doesn't work

Open mk1922 opened this issue 5 years ago • 1 comments

Hey! Thank you very much for the implementation of the network. I tried to run the test script with an image from the celeb dataset but it seems that the checkpoints (that were downloaded with download.py) don't fit the current architecture. I get the following error:

InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

Assign requires shapes of both tensors to match. lhs shape= [256] rhs shape= [64] [[node save/Assign_93 (defined at test.py:68) ]] [[node save/RestoreV2 (defined at test.py:68) ]]

Can anyone tell me how to adapt the network such that it fits the pre-trained weights? Thanks!

mk1922 avatar Aug 19 '19 14:08 mk1922

There was a bug in the code so the old weights won't fit into the network right now. The model's being trained again. Once it finishes, I'll update the weights as well. Thanks

shinseung428 avatar Aug 20 '19 08:08 shinseung428