def test_simple_rnn(self):
np.random.seed(12082518)
x = np.random.rand(128, 8, 32)
#
X = K.placeholder(shape=(None, 8, 32))
X1 = K.placeholder(shape=(None, 8, 32))
X2 = K.placeholder(shape=(None, 8, 32))
X3 = K.placeholder(shape=(None, 8, 33))
f = N.RNN(32, activation=K.relu, input_mode='skip')
#
y = f(X, mask=K.ones(shape=(128, 8)))
graph = K.ComputationGraph(y)
self.assertEqual(len(graph.inputs), 1)
f1 = K.function([X], y)
x1 = f1(x)
# ====== different placeholder ====== #
y = f(X1)
f2 = K.function([X1], y)
x2 = f1(x)
self.assertEqual(np.sum(x1[0] == x2[0]), np.prod(x1[0].shape))
# ====== pickle load ====== #
f = cPickle.loads(cPickle.dumps(f))
y = f(X2)
f2 = K.function([X2], y)
x3 = f2(x)
self.assertEqual(np.sum(x2[0] == x3[0]), np.prod(x2[0].shape))
# ====== other input shape ====== #
error_happen = False
try:
y = f(X3)
f3 = K.function([X3], y)
x3 = f3(np.random.rand(128, 8, 33))
except (ValueError, Exception):
error_happen = True
self.assertTrue(error_happen)
def test_rnn_decorator(self):
@K.rnn_decorator(sequences='X', states='out')
def rnn(X, out):
return K.relu(X + out)
y = rnn(K.ones(shape=(25, 12, 18, 8)), K.zeros(shape=(25, 18, 8)))
f = K.function([], y)
self.assertEqual(f()[0].shape, (25, 12, 18, 8))
def test_cudnn_rnn_nnet(self):
if get_device() == 'cpu':
return
print()
np.random.seed(1208)
batch_size = 6
hidden_size = 4
X_linear = K.placeholder(shape=(None, 3, 8), name='X_linear')
X_skip = K.placeholder(shape=(None, 3, hidden_size), name='X_skip')
for direction_mode in ['bidirectional', 'unidirectional']:
is_bidirectional = direction_mode == 'bidirectional'
for nb_layers in [2]:
real_layers = nb_layers * 2 if is_bidirectional else nb_layers
for rnn_mode in ['gru', 'lstm', 'rnn_relu', 'rnn_tanh']:
for init_state, init_state_name in zip(
[
None, # None init
K.init.uniform, # function init
K.variable(
np.random.rand(real_layers, 1,
hidden_size)), # variable
K.variable(
np.random.rand(real_layers, batch_size,
hidden_size)), # variable
K.zeros(shape=(real_layers, 1, hidden_size)),
K.ones(shape=(real_layers, batch_size,
hidden_size))
],
[
'None', 'Function', 'Var1', 'VarB', 'Tensor1',
'TensorB'
]):
for input_mode in ['linear', 'skip']:
if input_mode == 'linear':
X = X_linear
x = np.random.rand(batch_size, 3, 8)
else:
X = X_skip
x = np.random.rand(batch_size, 3, hidden_size)
start = timeit.default_timer()
f = N.CudnnRNN(num_units=hidden_size,
rnn_mode=rnn_mode,
input_mode=input_mode,
num_layers=nb_layers,
direction_mode=direction_mode,
params_split=False,
return_states=True)
# perform function
y = f(X, h0=init_state, c0=init_state)
f = K.function(X, y)
output = f(x)
benchmark = timeit.default_timer() - start
self.assertTrue([list(i.shape)
for i in output] == [[
batch_size if j is None else j
for j in K.get_shape(i)
] for i in y])
print(
"*PASSED* [Layers]%s [Mode]%-8s [Input]%-6s [Direction]%-12s [State]%s [Benchmark]%.4f"
% (nb_layers, rnn_mode, input_mode,
direction_mode, init_state_name, benchmark))
def convolutional_vae(X, saved_states, **kwargs):
""" convolutional_vae
Return
------
[y_encoder, y_decoder]
States
------
[f_inference (encoder), f_generative (decoder)]
"""
n = kwargs.get('n', 10)
batch_size = K.get_shape(X)[0]
if batch_size is None:
raise ValueError("You must specify batch_size dimension for the input placeholder.")
# ====== init ====== #
if saved_states is None:
# Encoder
f_inference = N.Sequence([
N.Reshape(shape=(-1, 28, 28, 1)),
N.Conv(num_filters=32, filter_size=3, strides=1, pad='valid',
b_init=init_ops.constant_initializer(0.), activation=K.elu),
N.Conv(num_filters=64, filter_size=5, strides=2, pad='same',
b_init=init_ops.constant_initializer(0.), activation=K.elu),
N.Dropout(level=0.1),
N.Flatten(outdim=2),
N.Dense(num_units=n * 2, b_init=None),
N.BatchNorm(axes=0)
], debug=True, name='Encoder')
# Decoder
f_generative = N.Sequence([
N.Dimshuffle(pattern=(0, 'x', 'x', 1)),
N.TransposeConv(num_filters=64, filter_size=3, strides=1, pad='valid',
b_init=init_ops.constant_initializer(0.), activation=K.elu),
N.TransposeConv(num_filters=32, filter_size=5, strides=2, pad='same',
b_init=init_ops.constant_initializer(0.), activation=K.elu),
N.TransposeConv(num_filters=1, filter_size=13, strides=3, pad='valid',
b_init=None),
N.BatchNorm(activation=K.linear),
N.Flatten(outdim=3)
], debug=True, name="Decoder")
else:
f_inference, f_generative = saved_states
# ====== Perfrom ====== #
# Encoder
y_encoder = f_inference(K.cast(X, 'float32'))
mu = y_encoder[:, :n]
sigma = K.softplus(y_encoder[:, n:])
qz = Normal(mu=mu, sigma=sigma, name='Normal_qz')
# Decoder
z = Normal(mu=K.zeros(shape=(batch_size, n)),
sigma=K.ones(shape=(batch_size, n)), name="Normal_pz")
logits = f_generative(z)
X_reconstruct = Bernoulli(logits=logits)
# inference
params = f_inference.parameters + f_generative.parameters
inference = ed.KLqp(latent_vars={z: qz}, data={X_reconstruct: X})
# ====== get cost for training ====== #
# Bind p(x, z) and q(z | x) to the same placeholder for x.
if K.is_training():
import tensorflow as tf
inference.initialize()
if True:
optimizer = tf.train.AdamOptimizer(0.01, epsilon=1.0)
updates = optimizer.apply_gradients(
optimizer.compute_gradients(inference.loss, var_list=params))
init = tf.global_variables_initializer()
init.run()
f_train = K.function(X, inference.loss, updates)
else:
optimizer = tf.train.AdamOptimizer(0.01, epsilon=1.0)
inference.initialize(optimizer=optimizer, var_list=params)
init = tf.global_variables_initializer()
init.run()
f_train = lambda x: inference.update(feed_dict={X: x})['loss']
samples = K.sigmoid(logits)
return (samples, z, qz), (f_inference, f_generative)
def convolutional_vae(X, saved_states, **kwargs):
""" convolutional_vae
Return
------
[y_encoder, y_decoder]
States
------
[f_inference (encoder), f_generative (decoder)]
"""
n = kwargs.get('n', 10)
batch_size = K.get_shape(X)[0]
if batch_size is None:
raise ValueError(
"You must specify batch_size dimension for the input placeholder.")
# ====== init ====== #
if saved_states is None:
# Encoder
f_inference = N.Sequence([
N.Reshape(shape=(-1, 28, 28, 1)),
N.Conv(num_filters=32,
filter_size=3,
strides=1,
pad='valid',
b_init=init_ops.constant_initializer(0.),
activation=K.elu),
N.Conv(num_filters=64,
filter_size=5,
strides=2,
pad='same',
b_init=init_ops.constant_initializer(0.),
activation=K.elu),
N.Dropout(level=0.1),
N.Flatten(outdim=2),
N.Dense(num_units=n * 2, b_init=None),
N.BatchNorm(axes=0)
],
debug=True,
name='Encoder')
# Decoder
f_generative = N.Sequence([
N.Dimshuffle(pattern=(0, 'x', 'x', 1)),
N.TransposeConv(num_filters=64,
filter_size=3,
strides=1,
pad='valid',
b_init=init_ops.constant_initializer(0.),
activation=K.elu),
N.TransposeConv(num_filters=32,
filter_size=5,
strides=2,
pad='same',
b_init=init_ops.constant_initializer(0.),
activation=K.elu),
N.TransposeConv(num_filters=1,
filter_size=13,
strides=3,
pad='valid',
b_init=None),
N.BatchNorm(activation=K.linear),
N.Flatten(outdim=3)
],
debug=True,
name="Decoder")
else:
f_inference, f_generative = saved_states
# ====== Perfrom ====== #
# Encoder
y_encoder = f_inference(K.cast(X, 'float32'))
mu = y_encoder[:, :n]
sigma = K.softplus(y_encoder[:, n:])
qz = Normal(mu=mu, sigma=sigma, name='Normal_qz')
# Decoder
z = Normal(mu=K.zeros(shape=(batch_size, n)),
sigma=K.ones(shape=(batch_size, n)),
name="Normal_pz")
logits = f_generative(z)
X_reconstruct = Bernoulli(logits=logits)
# inference
params = f_inference.parameters + f_generative.parameters
inference = ed.KLqp(latent_vars={z: qz}, data={X_reconstruct: X})
# ====== get cost for training ====== #
# Bind p(x, z) and q(z | x) to the same placeholder for x.
if K.is_training():
import tensorflow as tf
inference.initialize()
if True:
optimizer = tf.train.AdamOptimizer(0.01, epsilon=1.0)
updates = optimizer.apply_gradients(
optimizer.compute_gradients(inference.loss, var_list=params))
init = tf.global_variables_initializer()
init.run()
f_train = K.function(X, inference.loss, updates)
else:
optimizer = tf.train.AdamOptimizer(0.01, epsilon=1.0)
inference.initialize(optimizer=optimizer, var_list=params)
init = tf.global_variables_initializer()
init.run()
f_train = lambda x: inference.update(feed_dict={X: x})['loss']
samples = K.sigmoid(logits)
return (samples, z, qz), (f_inference, f_generative)