issue with loss_weights parameter of model.compile() , when model returns multiple output #67405
Labels
comp:keras
Keras related issues
stale
This label marks the issue/pr stale - to be closed automatically if no activity
stat:awaiting response
Status - Awaiting response from author
TF 2.11
Issues related to TF 2.11
type:support
Support issues
Issue type
Bug
Have you reproduced the bug with TensorFlow Nightly?
No
Source
binary
TensorFlow version
2.11.0
Custom code
Yes
OS platform and distribution
ubuntu 18.04
Mobile device
No response
Python version
3.7.5
Bazel version
No response
GCC/compiler version
7.5.0
CUDA/cuDNN version
cuda_11.8/cuDNN 9.1.0.70
GPU model and memory
Tesla P40/ 24 gb
Current behavior?
Even if i have provided the loss_weights parameter , TensorFlow 2.11.0 is calculating loss for each of the output variable in the outputs list against the true value .
Standalone code to reproduce the issue
Relevant log output
The text was updated successfully, but these errors were encountered: