To solve the error message, replace input_dim by inputs as keras.model() parameter.

For the problem with the loss value becoming NaN after 3 epochs:

• first check that there is no NaN in your data but as the first epochs run it should be the case

• probably that you are dealing with exploding gradients. Several possible solutions to try:

  • replace ReLU by tanh

  • decrease the learning rate

  • add gradient clipping

  • add weights regularisation