def testTopologicalAttributesMultiInputLayer(self):
class AddLayer(keras.layers.Layer):
def call(self, inputs):
assert len(inputs) == 2
return inputs[0] + inputs[1]
a = keras.Input(shape=(32, ))
b = keras.Input(shape=(32, ))
test_layer = AddLayer()
y = test_layer([a, b]) # pylint: disable=not-callable
self.assertEqual(test_layer.input, [a, b])
self.assertEqual(test_layer.output, y)
self.assertEqual(test_layer.input_shape, [(None, 32), (None, 32)])
self.assertEqual(test_layer.output_shape, (None, 32))
def get_functional_graph_model(input_dim, num_classes): # A simple functional-API model (a.k.a. graph network) inputs = keras.Input(shape=(input_dim,)) x = keras.layers.Dense(32, activation='relu')(inputs) x = keras.layers.BatchNormalization()(x) outputs = keras.layers.Dense(num_classes)(x) return keras.Model(inputs, outputs)
def test_is_keras_tensor(self):
x = keras.backend.variable(1)
self.assertEqual(keras.backend.is_keras_tensor(x), False)
x = keras.Input(shape=(1,))
self.assertEqual(keras.backend.is_keras_tensor(x), True)
with self.assertRaises(ValueError):
keras.backend.is_keras_tensor(0)
def get_nested_model_3(input_dim, num_classes):
# A functional-API model with a subclassed model inside.
# NOTE: this requires the inner subclass to implement `compute_output_shape`.
inputs = keras.Input(shape=(input_dim,))
x = keras.layers.Dense(32, activation='relu')(inputs)
x = keras.layers.BatchNormalization()(x)
class Inner(keras.Model):
def __init__(self):
super(Inner, self).__init__()
self.dense1 = keras.layers.Dense(32, activation='relu')
self.dense2 = keras.layers.Dense(5, activation='relu')
self.bn = keras.layers.BatchNormalization()
def call(self, inputs):
x = self.dense1(inputs)
x = self.dense2(x)
return self.bn(x)
def compute_output_shape(self, input_shape):
return tensor_shape.TensorShape((input_shape[0], 5))
test_model = Inner()
x = test_model(x) # pylint: disable=not-callable
outputs = keras.layers.Dense(num_classes)(x)
return keras.Model(inputs, outputs, name='nested_model_3')
def test_minimal_rnn_cell_non_layer(self):
class MinimalRNNCell(object):
def __init__(self, units, input_dim):
self.units = units
self.state_size = units
self.kernel = keras.backend.variable(
np.random.random((input_dim, units)))
def call(self, inputs, states):
prev_output = states[0]
output = keras.backend.dot(inputs, self.kernel) + prev_output
return output, [output]
with self.test_session():
# Basic test case.
cell = MinimalRNNCell(32, 5)
x = keras.Input((None, 5))
layer = keras.layers.RNN(cell)
y = layer(x)
model = keras.models.Model(x, y)
model.compile(optimizer='rmsprop', loss='mse')
model.train_on_batch(np.zeros((6, 5, 5)), np.zeros((6, 32)))
# Test stacking.
cells = [
MinimalRNNCell(8, 5),
MinimalRNNCell(32, 8),
MinimalRNNCell(32, 32)
]
layer = keras.layers.RNN(cells)
y = layer(x)
model = keras.models.Model(x, y)
model.compile(optimizer='rmsprop', loss='mse')
model.train_on_batch(np.zeros((6, 5, 5)), np.zeros((6, 32)))
def test_using_tf_layers_in_keras_functional_model(self):
with self.test_session():
np.random.seed(1337)
(x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
train_samples=200,
test_samples=100,
input_shape=(10, ),
num_classes=2)
y_train = keras.utils.to_categorical(y_train)
y_test = keras.utils.to_categorical(y_test)
inputs = keras.Input(shape=(10, ))
x = tf_core_layers.Dense(32, activation=nn.relu)(inputs)
outputs = tf_core_layers.Dense(2, activation=nn.softmax)(x)
model = keras.Model(inputs, outputs)
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
history = model.fit(x_train,
y_train,
epochs=10,
batch_size=16,
validation_data=(x_test, y_test),
verbose=0)
self.assertGreater(history.history['val_acc'][-1], 0.85)
def test_Bidirectional_state_reuse(self):
rnn = keras.layers.LSTM
samples = 2
dim = 5
timesteps = 3
units = 3
with self.test_session():
inputs = keras.Input((timesteps, dim))
layer = keras.layers.Bidirectional(
rnn(units, return_state=True, return_sequences=True))
outputs = layer(inputs)
output, state = outputs[0], outputs[1:]
# test passing invalid initial_state: passing a tensor
with self.assertRaises(ValueError):
output = keras.layers.Bidirectional(rnn(units))(
output, initial_state=state[0])
# test valid usage: passing a list
output = keras.layers.Bidirectional(rnn(units))(
output, initial_state=state)
model = keras.Model(inputs, output)
inputs = np.random.rand(samples, timesteps, dim)
outputs = model.predict(inputs)
def test_clone_sequential_model(self):
with self.test_session():
val_a = np.random.random((10, 4))
val_out = np.random.random((10, 4))
model = keras.models.Sequential()
model.add(keras.layers.Dense(4, input_shape=(4, )))
model.add(keras.layers.Dropout(0.5))
model.add(keras.layers.Dense(4))
# Everything should work in a new session.
keras.backend.clear_session()
with self.test_session():
# With placeholder creation
new_model = keras.models.clone_model(model)
new_model.compile('rmsprop', 'mse')
new_model.train_on_batch(val_a, val_out)
# On top of new tensor
input_a = keras.Input(shape=(4, ))
new_model = keras.models.clone_model(model, input_tensors=input_a)
new_model.compile('rmsprop', 'mse')
new_model.train_on_batch(val_a, val_out)
# On top of new, non-Keras tensor
input_a = keras.backend.variable(val_a)
new_model = keras.models.clone_model(model, input_tensors=input_a)
new_model.compile('rmsprop', 'mse')
new_model.train_on_batch(None, val_out)
def test_layer_sharing_at_heterogenous_depth_with_concat(self):
with self.test_session():
input_shape = (16, 9, 3)
input_layer = keras.Input(shape=input_shape)
a = keras.layers.Dense(3, name='dense_A')
b = keras.layers.Dense(3, name='dense_B')
c = keras.layers.Dense(3, name='dense_C')
x1 = b(a(input_layer))
x2 = a(c(input_layer))
output = keras.layers.concatenate([x1, x2])
m = keras.models.Model(inputs=input_layer, outputs=output)
x_val = np.random.random((10, 16, 9, 3))
output_val = m.predict(x_val)
config = m.get_config()
weights = m.get_weights()
m2 = keras.models.Model.from_config(config)
m2.set_weights(weights)
output_val_2 = m2.predict(x_val)
self.assertAllClose(output_val, output_val_2, atol=1e-6)
def test_get_updates_bn(self):
x1 = keras.Input(shape=(1, ))
layer = keras.layers.BatchNormalization()
_ = layer.apply(x1)
print('BN updates', layer._updates)
self.assertEqual(len(layer.updates), 2)
self.assertEqual(len(layer.get_updates_for(x1)), 2)
self.assertEqual(len(layer.get_updates_for(None)), 0)
def test_saving_model_with_long_weights_names(self):
if h5py is None:
return # Skip test if models cannot be saved.
with self.test_session():
x = keras.Input(shape=(2,), name='nested_model_input')
f = x
for i in range(4):
f = keras.layers.Dense(2, name='nested_model_dense_%d' % (i,))(f)
# This layer name will make the `weights_name`
# HDF5 attribute blow out of proportion.
f = keras.layers.Dense(2, name='nested_model_output' + ('x' * (2**14)))(f)
nested_model = keras.Model(inputs=[x], outputs=[f], name='nested_model')
x = keras.Input(shape=(2,), name='outer_model_input')
f = nested_model(x)
f = keras.layers.Dense(2, name='outer_model_output')(f)
model = keras.Model(inputs=[x], outputs=[f])
model.compile(loss='mse', optimizer='adam', metrics=['acc'])
x = np.random.random((1, 2))
y = np.random.random((1, 2))
model.train_on_batch(x, y)
out = model.predict(x)
fd, fname = tempfile.mkstemp('.h5')
keras.models.save_model(model, fname)
model = keras.models.load_model(fname)
# Check that the HDF5 files contains chunked array
# of weight names.
with h5py.File(fname, 'r') as h5file:
num_weight_arrays = len(
[attr for attr in h5file['model_weights']['nested_model'].attrs
if attr.startswith('weight_names')])
# The chunking of layer names array should have happend.
self.assertGreater(num_weight_arrays, 0)
out2 = model.predict(x)
self.assertAllClose(out, out2, atol=1e-05)
# Cleanup
os.close(fd)
os.remove(fname)
def test_conv_lstm(self):
num_row = 3
num_col = 3
filters = 2
num_samples = 1
input_channel = 2
input_num_row = 5
input_num_col = 5
sequence_len = 2
for data_format in ['channels_first', 'channels_last']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, sequence_len,
input_channel, input_num_row,
input_num_col)
else:
inputs = np.random.rand(num_samples, sequence_len,
input_num_row, input_num_col,
input_channel)
for return_sequences in [True, False]:
with self.test_session():
# test for return state:
x = keras.Input(batch_shape=inputs.shape)
kwargs = {
'data_format': data_format,
'return_sequences': return_sequences,
'return_state': True,
'stateful': True,
'filters': filters,
'kernel_size': (num_row, num_col),
'padding': 'valid'
}
layer = keras.layers.ConvLSTM2D(**kwargs)
layer.build(inputs.shape)
outputs = layer(x)
_, states = outputs[0], outputs[1:]
self.assertEqual(len(states), 2)
model = keras.models.Model(x, states[0])
state = model.predict(inputs)
self.assertAllClose(keras.backend.eval(layer.states[0]),
state,
atol=1e-4)
# test for output shape:
testing_utils.layer_test(keras.layers.ConvLSTM2D,
kwargs={
'data_format': data_format,
'return_sequences':
return_sequences,
'filters': filters,
'kernel_size':
(num_row, num_col),
'padding': 'valid'
},
input_shape=inputs.shape)
def test_clone_functional_model(self):
with self.test_session():
val_a = np.random.random((10, 4))
val_b = np.random.random((10, 4))
val_out = np.random.random((10, 4))
input_a = keras.Input(shape=(4, ))
input_b = keras.Input(shape=(4, ))
dense_1 = keras.layers.Dense(4, )
dense_2 = keras.layers.Dense(4, )
x_a = dense_1(input_a)
x_a = keras.layers.Dropout(0.5)(x_a)
x_b = dense_1(input_b)
x_a = dense_2(x_a)
outputs = keras.layers.add([x_a, x_b])
model = keras.models.Model([input_a, input_b], outputs)
# Everything should work in a new session.
keras.backend.clear_session()
with self.test_session():
# With placeholder creation
new_model = keras.models.clone_model(model)
new_model.compile('rmsprop', 'mse')
new_model.train_on_batch([val_a, val_b], val_out)
# On top of new tensors
input_a = keras.Input(shape=(4, ), name='a')
input_b = keras.Input(shape=(4, ), name='b')
new_model = keras.models.clone_model(
model, input_tensors=[input_a, input_b])
new_model.compile('rmsprop', 'mse')
new_model.train_on_batch([val_a, val_b], val_out)
# On top of new, non-Keras tensors
input_a = keras.backend.variable(val_a)
input_b = keras.backend.variable(val_b)
new_model = keras.models.clone_model(
model, input_tensors=[input_a, input_b])
new_model.compile('rmsprop', 'mse')
new_model.train_on_batch(None, val_out)
def test_activity_regularization_with_model_composition(self):
def reg(x):
return keras.backend.sum(x)
net_a_input = keras.Input((2, ))
net_a = net_a_input
net_a = keras.layers.Dense(2,
kernel_initializer='ones',
use_bias=False,
activity_regularizer=reg)(net_a)
model_a = keras.Model([net_a_input], [net_a])
net_b_input = keras.Input((2, ))
net_b = model_a(net_b_input)
model_b = keras.Model([net_b_input], [net_b])
model_b.compile(optimizer='sgd', loss=None)
x = np.ones((1, 2))
loss = model_b.evaluate(x)
self.assertEqual(loss, 4.)
def test_specify_state_with_masking(self):
num_states = 2
timesteps = 3
embedding_dim = 4
units = 3
num_samples = 2
with self.test_session():
inputs = keras.Input((timesteps, embedding_dim))
_ = keras.layers.Masking()(inputs)
initial_state = [keras.Input((units,)) for _ in range(num_states)]
output = keras.layers.LSTM(units)(inputs, initial_state=initial_state)
model = keras.models.Model([inputs] + initial_state, output)
model.compile(loss='categorical_crossentropy', optimizer='adam')
inputs = np.random.random((num_samples, timesteps, embedding_dim))
initial_state = [np.random.random((num_samples, units))
for _ in range(num_states)]
targets = np.random.random((num_samples, units))
model.train_on_batch([inputs] + initial_state, targets)
def test_Bidirectional_with_constants(self):
with self.test_session():
# Test basic case.
x = keras.Input((5, 5))
c = keras.Input((3, ))
cell = _RNNCellWithConstants(32)
custom_objects = {'_RNNCellWithConstants': _RNNCellWithConstants}
with keras.utils.CustomObjectScope(custom_objects):
layer = keras.layers.Bidirectional(keras.layers.RNN(cell))
y = layer(x, constants=c)
model = keras.Model([x, c], y)
model.compile(optimizer='rmsprop', loss='mse')
model.train_on_batch([np.zeros(
(6, 5, 5)), np.zeros((6, 3))], np.zeros((6, 64)))
# Test basic case serialization.
x_np = np.random.random((6, 5, 5))
c_np = np.random.random((6, 3))
y_np = model.predict([x_np, c_np])
weights = model.get_weights()
config = layer.get_config()
with keras.utils.CustomObjectScope(custom_objects):
layer = keras.layers.Bidirectional.from_config(
copy.deepcopy(config))
y = layer(x, constants=c)
model = keras.Model([x, c], y)
model.set_weights(weights)
y_np_2 = model.predict([x_np, c_np])
self.assertAllClose(y_np, y_np_2, atol=1e-4)
# Test flat list inputs
with keras.utils.CustomObjectScope(custom_objects):
layer = keras.layers.Bidirectional.from_config(
copy.deepcopy(config))
y = layer([x, c])
model = keras.Model([x, c], y)
model.set_weights(weights)
y_np_3 = model.predict([x_np, c_np])
self.assertAllClose(y_np, y_np_3, atol=1e-4)
def test_learning_phase(self):
with self.test_session() as sess:
keras.backend.set_learning_phase(1)
self.assertEqual(keras.backend.learning_phase(), 1)
with self.assertRaises(ValueError):
keras.backend.set_learning_phase(2)
# Test running with a learning-phase-consuming layer
keras.backend.set_learning_phase(0)
x = keras.Input((3,))
y = keras.layers.BatchNormalization()(x)
sess.run(variables.global_variables_initializer())
sess.run(y, feed_dict={x: np.random.random((2, 3))})
def test_state_reuse_with_dropout(self):
layer_class = keras.layers.SimpleRNN
embedding_dim = 4
units = 3
timesteps = 2
num_samples = 2
with self.test_session():
input1 = keras.Input(batch_shape=(num_samples, timesteps, embedding_dim))
layer = layer_class(units,
return_state=True,
return_sequences=True,
dropout=0.2)
state = layer(input1)[1:]
input2 = keras.Input(batch_shape=(num_samples, timesteps, embedding_dim))
output = layer_class(units)(input2, initial_state=state)
model = keras.Model([input1, input2], output)
inputs = [np.random.random((num_samples, timesteps, embedding_dim)),
np.random.random((num_samples, timesteps, embedding_dim))]
model.predict(inputs)
def test_stacked_rnn_dropout(self):
cells = [keras.layers.LSTMCell(3, dropout=0.1, recurrent_dropout=0.1),
keras.layers.LSTMCell(3, dropout=0.1, recurrent_dropout=0.1)]
layer = keras.layers.RNN(cells)
with self.test_session():
x = keras.Input((None, 5))
y = layer(x)
model = keras.models.Model(x, y)
model.compile('sgd', 'mse')
x_np = np.random.random((6, 5, 5))
y_np = np.random.random((6, 3))
model.train_on_batch(x_np, y_np)
def testTopologicalAttributesMultiOutputLayer(self):
class PowersLayer(keras.layers.Layer):
def call(self, inputs):
return [inputs**2, inputs**3]
x = keras.Input(shape=(32, ))
test_layer = PowersLayer()
p1, p2 = test_layer(x) # pylint: disable=not-callable
self.assertEqual(test_layer.input, x)
self.assertEqual(test_layer.output, [p1, p2])
self.assertEqual(test_layer.input_shape, (None, 32))
self.assertEqual(test_layer.output_shape, [(None, 32), (None, 32)])
def test_stacked_rnn_attributes(self):
cells = [keras.layers.LSTMCell(1), keras.layers.LSTMCell(1)]
layer = keras.layers.RNN(cells)
layer.build((None, None, 1))
# Test weights
self.assertEqual(len(layer.trainable_weights), 6)
cells[0].trainable = False
self.assertEqual(len(layer.trainable_weights), 3)
self.assertEqual(len(layer.non_trainable_weights), 3)
# Test `get_losses_for` and `losses`
x = keras.Input((None, 1))
loss_1 = math_ops.reduce_sum(x)
loss_2 = math_ops.reduce_sum(cells[0].kernel)
cells[0].add_loss(loss_1, inputs=x)
cells[0].add_loss(loss_2)
self.assertEqual(len(layer.losses), 2)
self.assertEqual(layer.get_losses_for(None), [loss_2])
self.assertEqual(layer.get_losses_for(x), [loss_1])
# Test `get_updates_for` and `updates`
cells = [keras.layers.LSTMCell(1), keras.layers.LSTMCell(1)]
layer = keras.layers.RNN(cells)
layer.build((None, None, 1))
x = keras.Input((None, 1))
update_1 = state_ops.assign_add(cells[0].kernel,
x[0, 0, 0] * cells[0].kernel)
update_2 = state_ops.assign_add(cells[0].kernel,
array_ops.ones_like(cells[0].kernel))
cells[0].add_update(update_1, inputs=x)
cells[0].add_update(update_2)
self.assertEqual(len(layer.updates), 2)
self.assertEqual(len(layer.get_updates_for(None)), 1)
self.assertEqual(len(layer.get_updates_for(x)), 1)
def test_multi_gpu_test_multi_io_model(self):
gpus = 2
num_samples = 1000
input_dim_a = 10
input_dim_b = 5
output_dim_a = 1
output_dim_b = 2
hidden_dim = 10
epochs = 2
target_gpu_id = [0, 1]
if not check_if_compatible_devices(gpus=gpus):
return
with self.test_session():
input_a = keras.Input((input_dim_a,))
input_b = keras.Input((input_dim_b,))
a = keras.layers.Dense(hidden_dim)(input_a)
b = keras.layers.Dense(hidden_dim)(input_b)
c = keras.layers.concatenate([a, b])
output_a = keras.layers.Dense(output_dim_a)(c)
output_b = keras.layers.Dense(output_dim_b)(c)
model = keras.models.Model([input_a, input_b], [output_a, output_b])
a_x = np.random.random((num_samples, input_dim_a))
b_x = np.random.random((num_samples, input_dim_b))
a_y = np.random.random((num_samples, output_dim_a))
b_y = np.random.random((num_samples, output_dim_b))
parallel_model = keras.utils.multi_gpu_model(model, gpus=gpus)
parallel_model.compile(loss='mse', optimizer='rmsprop')
parallel_model.fit([a_x, b_x], [a_y, b_y], epochs=epochs)
parallel_model = keras.utils.multi_gpu_model(model, gpus=target_gpu_id)
parallel_model.compile(loss='mse', optimizer='rmsprop')
parallel_model.fit([a_x, b_x], [a_y, b_y], epochs=epochs)
def testTopologicalAttributes(self):
# test layer attributes / methods related to cross-layer connectivity.
a = keras.Input(shape=(32, ), name='input_a')
b = keras.Input(shape=(32, ), name='input_b')
# test input, output, input_shape, output_shape
test_layer = keras.layers.Dense(16, name='test_layer')
a_test = test_layer(a)
self.assertEqual(test_layer.input, a)
self.assertEqual(test_layer.output, a_test)
self.assertEqual(test_layer.input_shape, (None, 32))
self.assertEqual(test_layer.output_shape, (None, 16))
# test `get_*_at` methods
dense = keras.layers.Dense(16, name='dense_1')
a_2 = dense(a)
b_2 = dense(b)
self.assertEqual(dense.get_input_at(0), a)
self.assertEqual(dense.get_input_at(1), b)
self.assertEqual(dense.get_output_at(0), a_2)
self.assertEqual(dense.get_output_at(1), b_2)
self.assertEqual(dense.get_input_shape_at(0), (None, 32))
self.assertEqual(dense.get_input_shape_at(1), (None, 32))
self.assertEqual(dense.get_output_shape_at(0), (None, 16))
self.assertEqual(dense.get_output_shape_at(1), (None, 16))
# Test invalid value for attribute retrieval.
with self.assertRaises(ValueError):
dense.get_input_at(2)
with self.assertRaises(AttributeError):
new_dense = keras.layers.Dense(16)
_ = new_dense.input
with self.assertRaises(AttributeError):
new_dense = keras.layers.Dense(16)
_ = new_dense.output
with self.assertRaises(AttributeError):
new_dense = keras.layers.Dense(16)
_ = new_dense.output_shape
with self.assertRaises(AttributeError):
new_dense = keras.layers.Dense(16)
_ = new_dense.input_shape
with self.assertRaises(AttributeError):
new_dense = keras.layers.Dense(16)
a = keras.Input(shape=(3, 32))
a = keras.Input(shape=(5, 32))
a_2 = dense(a)
b_2 = dense(b)
_ = new_dense.input_shape
with self.assertRaises(AttributeError):
new_dense = keras.layers.Dense(16)
a = keras.Input(shape=(3, 32))
a = keras.Input(shape=(5, 32))
a_2 = dense(a)
b_2 = dense(b)
_ = new_dense.output_shape
def test_state_reuse(self):
timesteps = 3
embedding_dim = 4
units = 3
num_samples = 2
with self.test_session():
inputs = keras.Input(batch_shape=(num_samples, timesteps, embedding_dim))
layer = keras.layers.LSTM(units, return_state=True, return_sequences=True)
outputs = layer(inputs)
output, state = outputs[0], outputs[1:]
output = keras.layers.LSTM(units)(output, initial_state=state)
model = keras.models.Model(inputs, output)
inputs = np.random.random((num_samples, timesteps, embedding_dim))
outputs = model.predict(inputs)
def test_builtin_rnn_cell_serialization(self):
for cell_class in [keras.layers.SimpleRNNCell,
keras.layers.GRUCell,
keras.layers.LSTMCell]:
with self.test_session():
# Test basic case.
x = keras.Input((None, 5))
cell = cell_class(32)
layer = keras.layers.RNN(cell)
y = layer(x)
model = keras.models.Model(x, y)
model.compile(optimizer='rmsprop', loss='mse')
# Test basic case serialization.
x_np = np.random.random((6, 5, 5))
y_np = model.predict(x_np)
weights = model.get_weights()
config = layer.get_config()
layer = keras.layers.RNN.from_config(config)
y = layer(x)
model = keras.models.Model(x, y)
model.set_weights(weights)
y_np_2 = model.predict(x_np)
self.assertAllClose(y_np, y_np_2, atol=1e-4)
# Test stacking.
cells = [cell_class(8),
cell_class(12),
cell_class(32)]
layer = keras.layers.RNN(cells)
y = layer(x)
model = keras.models.Model(x, y)
model.compile(optimizer='rmsprop', loss='mse')
# Test stacked RNN serialization.
x_np = np.random.random((6, 5, 5))
y_np = model.predict(x_np)
weights = model.get_weights()
config = layer.get_config()
layer = keras.layers.RNN.from_config(config)
y = layer(x)
model = keras.models.Model(x, y)
model.set_weights(weights)
y_np_2 = model.predict(x_np)
self.assertAllClose(y_np, y_np_2, atol=1e-4)
def test_return_state(self):
num_states = 2
timesteps = 3
embedding_dim = 4
units = 3
num_samples = 2
with self.test_session():
inputs = keras.Input(batch_shape=(num_samples, timesteps, embedding_dim))
layer = keras.layers.LSTM(units, return_state=True, stateful=True)
outputs = layer(inputs)
state = outputs[1:]
assert len(state) == num_states
model = keras.models.Model(inputs, state[0])
inputs = np.random.random((num_samples, timesteps, embedding_dim))
state = model.predict(inputs)
self.assertAllClose(keras.backend.eval(layer.states[0]), state, atol=1e-4)
def test_model_cloning_invalid_use_cases(self):
seq_model = keras.models.Sequential()
seq_model.add(keras.layers.Dense(4, input_shape=(4,)))
x = keras.Input((4,))
y = keras.layers.Dense(4)(x)
fn_model = keras.models.Model(x, y)
with self.assertRaises(ValueError):
keras.models._clone_functional_model(seq_model)
with self.assertRaises(ValueError):
keras.models._clone_functional_model(None)
with self.assertRaises(ValueError):
keras.models._clone_sequential_model(fn_model)
with self.assertRaises(ValueError):
keras.models._clone_sequential_model(seq_model, input_tensors=[x, x])
with self.assertRaises(ValueError):
keras.models._clone_sequential_model(seq_model, input_tensors=y)
def test_saving_model_with_long_layer_names(self):
if h5py is None:
return # Skip test if models cannot be saved.
with self.test_session():
# This layer name will make the `layers_name` HDF5 attribute blow
# out of proportion. Note that it fits into the internal HDF5
# attribute memory limit on its own but because h5py converts
# the list of layer names into numpy array, which uses the same
# amout of memory for every item, it increases the memory
# requirements substantially.
x = keras.Input(shape=(2, ), name='input_' + ('x' * (2**15)))
f = x
for i in range(4):
f = keras.layers.Dense(2, name='dense_%d' % (i, ))(f)
model = keras.Model(inputs=[x], outputs=[f])
model.compile(loss='mse', optimizer='adam', metrics=['acc'])
x = np.random.random((1, 2))
y = np.random.random((1, 2))
model.train_on_batch(x, y)
out = model.predict(x)
fd, fname = tempfile.mkstemp('.h5')
keras.models.save_model(model, fname)
model = keras.models.load_model(fname)
# Check that the HDF5 files contains chunked array
# of layer names.
with h5py.File(fname, 'r') as h5file:
num_names_arrays = len([
attr for attr in h5file['model_weights'].attrs
if attr.startswith('layer_names')
])
# The chunking of layer names array should have happened.
self.assertGreater(num_names_arrays, 0)
out2 = model.predict(x)
self.assertAllClose(out, out2, atol=1e-05)
# Cleanup
os.close(fd)
os.remove(fname)
def test_return_state(self, layer_class):
if test.is_gpu_available(cuda_only=True):
with self.test_session(use_gpu=True):
input_size = 10
timesteps = 6
units = 2
num_samples = 32
num_states = 2 if layer_class is keras.layers.CuDNNLSTM else 1
inputs = keras.Input(batch_shape=(num_samples, timesteps, input_size))
layer = layer_class(units, return_state=True, stateful=True)
outputs = layer(inputs)
_, state = outputs[0], outputs[1:]
self.assertEqual(len(state), num_states)
model = keras.models.Model(inputs, state[0])
inputs = np.random.random((num_samples, timesteps, input_size))
state = model.predict(inputs)
np.testing.assert_allclose(
keras.backend.eval(layer.states[0]), state, atol=1e-4)
def test_layer_sharing_at_heterogenous_depth(self):
with self.test_session():
x_val = np.random.random((10, 5))
x = keras.Input(shape=(5, ))
a = keras.layers.Dense(5, name='A')
b = keras.layers.Dense(5, name='B')
output = a(b(a(b(x))))
m = keras.models.Model(x, output)
output_val = m.predict(x_val)
config = m.get_config()
weights = m.get_weights()
m2 = keras.models.Model.from_config(config)
m2.set_weights(weights)
output_val_2 = m2.predict(x_val)
self.assertAllClose(output_val, output_val_2, atol=1e-6)
