Problems when run tensorflow prediction of .pb

taki0112 / UGATIT

Official Tensorflow implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (ICLR 2020)

MIT License

6.17k stars 1.04k forks source link

Problems when run tensorflow prediction of .pb #71

Open DiMiTriFrog opened 4 years ago

DiMiTriFrog commented 4 years ago

I have a saved model .pb create by code of the issues and the size is 1.12GB When I'm trying to load the saved_model I have a issue:

tensorflow.python.framework.errors_impl.NotFoundError: Op type not registered 'IteratorGetDevice' in binary running on MacBook-Pro.local. Make sure the Op and Kernel are registered in the binary running in this process.

I don't know why and what I have to do :S

DiMiTriFrog commented 4 years ago

Not for the moment :(

ak9250 commented 4 years ago

@DiMiTriFrog were you able to solve this?