The model expects 3 channels but you provide 1 channel. ``` input = tf.keras.Input( shape=(256, 237, 1), name="input_mdrk_silhouette_continuous", ) ``` https://github.com/broadinstitute/ml4h/blob/master/model_zoo/silhouette_mri/train_models.py#L261 How do you account for the other 2 channels? @mklarqvist