TensorFlow in version 2.3 produces wrong model accuracy when the model is serialized
TensorFlow in version 2.3 produces wrong model accuracy when the model is
TensorFlow in version 2.3 fails to serialize the model properly. This resolves
in bad model accuracy when the model is loaded back. The issue is caused by a
accuracy which has been already resolved in more recent versions.
To avoid this issue, make sure you use
sparce_categorical_accuracy instead of
accuracy when compiling the model.
Compile the model using
sparce_categorical_accuracy instead of just
- model.compile(..., metrics=['accuracy']) + model.compile(..., metrics=['sparce_categorical_accuracy'])
This message can be produced for all the recommendation types.