Why MES loss is nan in training?

[bestl1fe]

When I trained 120 size images to epoch 30, nan appeared and all images turned black. I didn't save the model for each training, so I had to retrain my model.

I think we should add a way to prevent nan.

[chairc]

Good work. Could you submit a pr for this issue?

[chairc]

The possible reasons for this problem may include an excessively high learning rate, unstable operations in the loss function, issues with the activation function, etc. Of course, future versions will be updated to include a check for NaN values.

[chairc]

We submit a function for NaN detection #89