Error when running the model.fit on the wrapped model "Only input tensors may be passed as positional arguments."

[ashkanee]

When executing (it is the wrapped model):

model.fit(training_dataset, epochs=5) where
training_dataset = tf.data.Dataset.from_tensor_slices((training_input, training_output.T))

I get:

RuntimeError: Exception encountered when calling ModelWrapper.call(). Could not automatically infer the output shape / dtype of 'model_wrapper' (of type ModelWrapper). Either the ModelWrapper.call()method is incorrect, or you need to implement theModelWrapper.compute_output_spec() / compute_output_shape() method. Error encountered: Only input tensors may be passed as positional arguments. The following argument value should be passed as a keyword argument: None (of type <class 'NoneType'>) Arguments received by ModelWrapper.call(): • args=('<KerasTensor shape=(None,), dtype=float32, sparse=None, name=keras_tensor_10>',) • kwargs={'mask': 'None'}

Can you please help? Thanks

[ghsanti]

Can you provide a code example that we can test? @ashkanee