Loss turns to NaN - Githubissues

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

Loss turns to NaN #41

Closed Arkkienkeli closed 5 years ago

Arkkienkeli commented 5 years ago

Hi, loss of the network turns to nan after a view (100-200 iterations). I have about 250 images in dataset for this test run.

taki0112 commented 5 years ago

Maybe it's because of the small number of data. Or reduce the cam_weight.

gdwei commented 3 years ago

Same problem loss of the network turns to nan after 48k iterations.