Open innat opened 9 months ago
@innat, Thank you for reporting the issue. Could you please try to provide the PR for making these changes happen in the tf-keras as this issue is present only in keras2? Thank you!
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.
Hi, Im not open for the contribution. I found this from this https://stackoverflow.com/questions/77930212/multitask-learning-to-classify-on-dog-images/77935240#77935240
This behaviour happens in Keras 2 but works in Keras 3.
I tried to train a multi-output model. But it target looks like something as follows
Between this two target array,
-1
is paced toy2_dummy[0]
but some value iny1_dummy[0]
and continues. In training time, I setignore_class = -1
, please see below.The code works in Keras 3 but in Keras 2, the loss becomes
nan
. Below is the full code.