def testLSTMBlockCell(self):
with self.session(use_gpu=True, graph=tf.Graph()) as sess:
with tf.variable_scope("root",
initializer=tf.constant_initializer(0.5)):
x = tf.zeros([1, 2])
m0 = tf.zeros([1, 2])
m1 = tf.zeros([1, 2])
m2 = tf.zeros([1, 2])
m3 = tf.zeros([1, 2])
g, ((out_m0, out_m1),
(out_m2, out_m3)) = rnn_cell.MultiRNNCell(
[contrib_rnn.LSTMBlockCell(2) for _ in range(2)],
state_is_tuple=True)(x, ((m0, m1), (m2, m3)))
sess.run([tf.global_variables_initializer()])
res = sess.run(
[g, out_m0, out_m1, out_m2, out_m3], {
x.name: np.array([[1., 1.]]),
m0.name: 0.1 * np.ones([1, 2]),
m1.name: 0.1 * np.ones([1, 2]),
m2.name: 0.1 * np.ones([1, 2]),
m3.name: 0.1 * np.ones([1, 2])
})
self.assertLen(res, 5)
self.assertAllClose(res[0], [[0.24024698, 0.24024698]])
# These numbers are from testBasicLSTMCell and only test c/h.
self.assertAllClose(res[1], [[0.68967271, 0.68967271]])
self.assertAllClose(res[2], [[0.44848421, 0.44848421]])
self.assertAllClose(res[3], [[0.39897051, 0.39897051]])
self.assertAllClose(res[4], [[0.24024698, 0.24024698]])
def testLSTMBasicToBlockCell(self):
with self.session(use_gpu=True) as sess:
x = tf.zeros([1, 2])
x_values = np.random.randn(1, 2)
m0_val = 0.1 * np.ones([1, 2])
m1_val = -0.1 * np.ones([1, 2])
m2_val = -0.2 * np.ones([1, 2])
m3_val = 0.2 * np.ones([1, 2])
initializer = tf.random_uniform_initializer(-0.01,
0.01,
seed=19890212)
with tf.variable_scope("basic", initializer=initializer):
m0 = tf.zeros([1, 2])
m1 = tf.zeros([1, 2])
m2 = tf.zeros([1, 2])
m3 = tf.zeros([1, 2])
g, ((out_m0, out_m1),
(out_m2, out_m3)) = rnn_cell.MultiRNNCell(
[
rnn_cell.BasicLSTMCell(2, state_is_tuple=True)
for _ in range(2)
],
state_is_tuple=True)(x, ((m0, m1), (m2, m3)))
sess.run([tf.global_variables_initializer()])
basic_res = sess.run(
[g, out_m0, out_m1, out_m2, out_m3], {
x.name: x_values,
m0.name: m0_val,
m1.name: m1_val,
m2.name: m2_val,
m3.name: m3_val
})
with tf.variable_scope("block", initializer=initializer):
m0 = tf.zeros([1, 2])
m1 = tf.zeros([1, 2])
m2 = tf.zeros([1, 2])
m3 = tf.zeros([1, 2])
g, ((out_m0, out_m1),
(out_m2, out_m3)) = rnn_cell.MultiRNNCell(
[contrib_rnn.LSTMBlockCell(2) for _ in range(2)],
state_is_tuple=True)(x, ((m0, m1), (m2, m3)))
sess.run([tf.global_variables_initializer()])
block_res = sess.run(
[g, out_m0, out_m1, out_m2, out_m3], {
x.name: x_values,
m0.name: m0_val,
m1.name: m1_val,
m2.name: m2_val,
m3.name: m3_val
})
self.assertEqual(len(basic_res), len(block_res))
for basic, block in zip(basic_res, block_res):
self.assertAllClose(basic, block)
def rnn_cell(rnn_cell_size, dropout_keep_prob, residual, is_training=True):
"""Builds an LSTMBlockCell based on the given parameters."""
dropout_keep_prob = dropout_keep_prob if is_training else 1.0
cells = []
for i in range(len(rnn_cell_size)):
cell = contrib_rnn.LSTMBlockCell(rnn_cell_size[i])
if residual:
cell = rnn.ResidualWrapper(cell)
if i == 0 or rnn_cell_size[i] != rnn_cell_size[i - 1]:
cell = contrib_rnn.InputProjectionWrapper(
cell, rnn_cell_size[i])
cell = rnn.DropoutWrapper(cell, input_keep_prob=dropout_keep_prob)
cells.append(cell)
return rnn.MultiRNNCell(cells)
def testCompatibleNames(self):
with self.session(use_gpu=True, graph=tf.Graph()):
cell = rnn_cell.LSTMCell(10)
pcell = rnn_cell.LSTMCell(10, use_peepholes=True)
inputs = [tf.zeros([4, 5])] * 6
tf.nn.static_rnn(cell, inputs, dtype=tf.float32, scope="basic")
tf.nn.static_rnn(pcell, inputs, dtype=tf.float32, scope="peephole")
basic_names = {
v.name: v.get_shape()
for v in tf.trainable_variables()
}
with self.session(use_gpu=True, graph=tf.Graph()):
cell = contrib_rnn.LSTMBlockCell(10)
pcell = contrib_rnn.LSTMBlockCell(10, use_peephole=True)
inputs = [tf.zeros([4, 5])] * 6
tf.nn.static_rnn(cell, inputs, dtype=tf.float32, scope="basic")
tf.nn.static_rnn(pcell, inputs, dtype=tf.float32, scope="peephole")
block_names = {
v.name: v.get_shape()
for v in tf.trainable_variables()
}
self.assertEqual(basic_names, block_names)
def testNoneDimsWithDynamicRNN(self):
with self.session(use_gpu=True, graph=tf.Graph()) as sess:
batch_size = 4
num_steps = 5
input_dim = 6
cell_size = 7
cell = contrib_rnn.LSTMBlockCell(cell_size)
x = tf.placeholder(tf.float32, shape=(None, None, input_dim))
output, _ = tf.nn.dynamic_rnn(cell,
x,
time_major=True,
dtype=tf.float32)
sess.run(tf.global_variables_initializer())
feed = {}
feed[x] = np.random.randn(num_steps, batch_size, input_dim)
sess.run(output, feed)