Nicolas
Results
22
comments of
Nicolas
@tilakrayal I am still getting the error (with 2.18). Please note that the test is non-deterministic and there is a small probability of success.
This can be done using the new [structured loss feature](https://github.com/keras-team/keras/pull/20358): ```python import os os.environ["KERAS_BACKEND"] = "tensorflow" import numpy as np import keras from keras import layers from keras import ops...