[BUG] Conflicting loss_weights implementation in Keras3 for single output case.

[YUHSINCHENG1230]

Description when I trainnig a U-net model (Multiple class) with keras 3, in model.fit() step it have this probelm.

ValueError: When there is only a single output, the loss_weights argument must be a Python float. Received instead: loss_weights=[, ] of type.

but in karas 2 it run successfully. (same code)

Can anyone help me to solve this problem?

[chunduriv]

@YUHSINCHENG1230, Could you please share reproducible code?

[YUHSINCHENG1230]

I think I found the poblem and I solve it. but i have some question , why the result is not same in keras2 and 3?(same code)

[nkovela1]

Hi @YUHSINCHENG1230 , would you be able to provide reproducible code? It would helps us answer your question, thanks!

[github-actions[bot]]

This issue is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you.

[github-actions[bot]]

This issue was closed because it has been inactive for 28 days. Please reopen if you'd like to work on this further.

[google-ml-butler[bot]]

Are you satisfied with the resolution of your issue? Yes No