def qrnn_forward(self, X, size, n_class, batch_size, conv_size):
in_size = int(X.get_shape()[2])
qrnn = QRNN(in_size=in_size, size=size, conv_size=conv_size)
hidden = qrnn.forward(X)
with tf.name_scope("QRNN-Classifier"):
W = tf.Variable(tf.random_normal([size, n_class]), name="W")
b = tf.Variable(tf.random_normal([n_class]), name="b")
output = tf.add(tf.matmul(hidden, W), b)
return output
def test_qrnn_linear_forward(self):
batch_size = 100
sentence_length = 5
word_size = 10
size = 5
data = self.create_test_data(batch_size, sentence_length, word_size)
with tf.Graph().as_default() as q_linear:
qrnn = QRNN(in_size=word_size, size=size, conv_size=1)
X = tf.placeholder(tf.float32, [batch_size, sentence_length, word_size])
forward_graph = qrnn.forward(X)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
hidden = sess.run(forward_graph, feed_dict={X: data})
self.assertEqual((batch_size, size), hidden.shape)