Gradients do not exist for variables ['sync_batch_normalization_8/gamma:0', 'sync_batch_normalization_8/beta:0', 'conv3d_21/kernel:0', 'conv3d_21/bias:0']

[fahadahmedkhokhar]

I am using your custom defined model for training of the data. But before training start following error shows. Can you please address this issue?

prognosais WARNING Gradients do not exist for variables ['sync_batch_normalization_8/gamma:0', 'sync_batch_normalization_8/beta:0', 'conv3d_21/kernel:0', 'conv3d_21/bias:0'] when minimizing the loss. If you're using model.compile(), did you forget to provide a loss argument?

[Svdvoort]

I would need some more information about what you are trying to do:

• Which custom model are you using?
• What does your training script look like?

Based on this information my first two suggestions would be:

1. Did you provide a loss in the model.compile() as suggested by the error message?
2. Try lowering your learning learning rate, sometimes this can be the case as well.

[fahadahmedkhokhar]

I am using your custom_model.py file. I use the 0.001 learning rate as well but it doesn't work

[Svdvoort]

Closed in favor of #7