If I set loss_weights = 0 for all multiple outputs of a Keras model, how the loss function is computed? I am aware from Keras documentation about the definition: "The loss value that will be minimized by the model will then be the weighted sum of all individual losses, weighted by the loss_weights coefficients" but in this situation, I wonder what is actually the model trying to minimize?

Also, I am interested to know if possible to optimize independently, model's outputs, without having to optimize the sum of individual losses.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.