Currently, it seems this tool suppose validation to be NumPy arrays or Keras generator, while the tensorflow.data.Dataset is also one of the most frequently used input data structure which is not supported by this tool. I notice that the raised error comes from indexing, counting and sampling on validation dataset which belongs to tf.data.Dataset class. This should be very easy to solve. Could you please add this feature?
Currently, it seems this tool suppose validation to be NumPy arrays or Keras generator, while the tensorflow.data.Dataset is also one of the most frequently used input data structure which is not supported by this tool. I notice that the raised error comes from indexing, counting and sampling on validation dataset which belongs to tf.data.Dataset class. This should be very easy to solve. Could you please add this feature?