In wavenet.py's build_model()
if not learn_all_outputs: raise DeprecationWarning('Learning on just all outputs is wasteful, now learning only inside receptive field.'); out = layers.Lambda(lambda x: x[:, -1, :], output_shape=(out._keras_shape[-1],))( out) # Based on gif in deepmind blog: take last output?
you better do this before the two final 1x1 convolutional layers a few lines above to cut more waste, right?``
In wavenet.py's build_model()
if not learn_all_outputs: raise DeprecationWarning('Learning on just all outputs is wasteful, now learning only inside receptive field.'); out = layers.Lambda(lambda x: x[:, -1, :], output_shape=(out._keras_shape[-1],))( out) # Based on gif in deepmind blog: take last output?you better do this before the two final 1x1 convolutional layers a few lines above to cut more waste, right?``