Keras: Build Error Using TimeDistributed Recurrent Layer with Dropout

keras_distributed_rnn_dropout_error.py

import numpy
from keras.models import Model
from keras.layers import Input, Embedding, GRU, TimeDistributed

batch_size = 2
n_sequences = 5
n_elements_per_sequence = 7
element_size = 12

dropout_W = 0.5
dropout_U = 0

sequence_of_sequences_input = Input(batch_shape=(batch_size, None, None, element_size),
									name='sequence_of_sequences_input')

rnn_layer = GRU(20, return_sequences=False, dropout_W=dropout_W, dropout_U=dropout_U)

sequence_embeddings = TimeDistributed(rnn_layer, name="sequence_embeddings")(sequence_of_sequences_input)

model = Model(sequence_of_sequences_input, sequence_embeddings)
model.compile("adam", "mse")
model._make_predict_function()

X = numpy.random.rand(batch_size, n_sequences, n_elements_per_sequence, element_size)

Y = model.predict_on_batch(X)

model._make_predict_function() throwing an error when setting either dropout_W or dropout_U to a value > 0.