Python keras.backend.in_train_phase() Examples
The following are 30
code examples of keras.backend.in_train_phase().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
keras.backend
, or try the search function
.
.
Example #1
| Source File: rnnlayer.py From recurrent-attention-for-QA-SQUAD-based-on-keras with MIT License | 6 votes |
|
def get_constants(self, inputs, training=None):
constants = []
'''if 0 < self.dropout_U < 1:
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, self.units))
B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
constants.append(B_U)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
if 0 < self.dropout_W < 1:
input_shape = K.int_shape(x)
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, int(input_dim)))
B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
constants.append(B_W)
else:'''
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
return constants
Example #2
| Source File: lstm2ntm.py From NTM-Keras with MIT License | 6 votes |
|
def get_constants(self, x):
constants = []
if 0 < self.dropout_U < 1:
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, self.output_dim))
B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(4)]
constants.append(B_U)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(4)])
if 0 < self.dropout_W < 1:
input_shape = self.input_spec[0].shape
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, int(input_dim)))
B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(4)]
constants.append(B_W)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(4)])
return constants
Example #3
| Source File: layers.py From indic_tagger with Apache License 2.0 | 6 votes |
|
def call(self, X, mask=None):
if mask is not None:
assert K.ndim(mask) == 2, 'Input mask to CRF must have dim 2 if not None'
if self.test_mode == 'viterbi':
test_output = self.viterbi_decoding(X, mask)
else:
test_output = self.get_marginal_prob(X, mask)
self.uses_learning_phase = True
if self.learn_mode == 'join':
train_output = K.zeros_like(K.dot(X, self.kernel))
out = K.in_train_phase(train_output, test_output)
else:
if self.test_mode == 'viterbi':
train_output = self.get_marginal_prob(X, mask)
out = K.in_train_phase(train_output, test_output)
else:
out = test_output
return out
Example #4
| Source File: TTRNN.py From TT_RNN with MIT License | 6 votes |
|
def get_constants(self, inputs, training=None):
constants = []
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
if 0. < self.recurrent_dropout < 1:
ones = K.ones_like(K.reshape(inputs[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, self.units))
def dropped_inputs():
return K.dropout(ones, self.recurrent_dropout)
rec_dp_mask = [K.in_train_phase(dropped_inputs,
ones,
training=training) for _ in range(3)]
constants.append(rec_dp_mask)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
return constants
Example #5
| Source File: rbm.py From keras_bn_library with MIT License | 6 votes |
|
def sample_h_given_x(self, x):
h_pre = K.dot(x, self.Wrbm) + self.bh
h_sigm = self.activation(self.scaling_h_given_x * h_pre)
# drop out noise
#if(0.0 < self.p < 1.0):
# noise_shape = self._get_noise_shape(h_sigm)
# h_sigm = K.in_train_phase(K.dropout(h_sigm, self.p, noise_shape), h_sigm)
if(self.hidden_unit_type == 'binary'):
h_samp = K.random_binomial(shape=h_sigm.shape, p=h_sigm)
# random sample
# \hat{h} = 1, if p(h=1|x) > uniform(0, 1)
# 0, otherwise
elif(self.hidden_unit_type == 'nrlu'):
h_samp = nrlu(h_pre)
else:
h_samp = h_sigm
if(0.0 < self.p < 1.0):
noise_shape = self._get_noise_shape(h_samp)
h_samp = K.in_train_phase(K.dropout(h_samp, self.p, noise_shape), h_samp)
return h_samp, h_pre, h_sigm
Example #6
| Source File: layers.py From anago with MIT License | 6 votes |
|
def call(self, X, mask=None):
if mask is not None:
assert K.ndim(mask) == 2, 'Input mask to CRF must have dim 2 if not None'
if self.test_mode == 'viterbi':
test_output = self.viterbi_decoding(X, mask)
else:
test_output = self.get_marginal_prob(X, mask)
self.uses_learning_phase = True
if self.learn_mode == 'join':
train_output = K.zeros_like(K.dot(X, self.kernel))
out = K.in_train_phase(train_output, test_output)
else:
if self.test_mode == 'viterbi':
train_output = self.get_marginal_prob(X, mask)
out = K.in_train_phase(train_output, test_output)
else:
out = test_output
return out
Example #7
| Source File: rnnrbm.py From keras_bn_library with MIT License | 6 votes |
|
def get_constants(self, x):
constants = []
if 0 < self.dropout_U < 1:
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, self.hidden_recurrent_dim))
B_U = K.in_train_phase(K.dropout(ones, self.dropout_U), ones)
constants.append(B_U)
else:
constants.append(K.cast_to_floatx(1.))
if self.consume_less == 'cpu' and 0 < self.dropout_W < 1:
input_shape = self.input_spec[0].shape
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, input_dim))
B_W = K.in_train_phase(K.dropout(ones, self.dropout_W), ones)
constants.append(B_W)
else:
constants.append(K.cast_to_floatx(1.))
return constants
Example #8
| Source File: tgru_k2_gpu.py From chemical_vae with Apache License 2.0 | 6 votes |
|
def get_constants(self, inputs, training=None):
constants = []
if 0. < self.recurrent_dropout < 1.:
ones = K.ones_like(K.reshape(inputs[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, self.units))
def dropped_inputs():
return K.dropout(ones, self.recurrent_dropout)
rec_dp_mask = [K.in_train_phase(dropped_inputs,
ones,
training=training) for _ in range(3)]
constants.append(rec_dp_mask)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
return constants
Example #9
| Source File: transform_rnn.py From View-Adaptive-Neural-Networks-for-Skeleton-based-Human-Action-Recognition with MIT License | 6 votes |
|
def call(self,x,training=None):
deta1 = 0.3
deta2 = 0.3
deta3 = 0.3
seed = np.random.randint(1, 10e6)
rng = RandomStreams(seed=seed)
theta1 = rng.uniform(size=(x.shape[0],1),low=-deta1,high=deta1,dtype='float32')
theta2 = rng.uniform(size=(x.shape[0],1),low=-deta2,high=deta2,dtype='float32')
theta3 = rng.uniform(size=(x.shape[0],1),low=-deta3,high=deta3,dtype='float32')
theta = K.concatenate([theta1,theta2,theta3],axis=-1)
theta = K.tile(theta,x.shape[1])
theta = theta.reshape((x.shape[0], x.shape[1], 3))
theta = theta.reshape((theta.shape[0]*theta.shape[1], theta.shape[2]))
M = _fusion(theta)
output = _transform_rot(M, x)
return K.in_train_phase(output,x,training = training)
Example #10
| Source File: rhn.py From deep-models with Apache License 2.0 | 6 votes |
|
def get_constants(self, x):
constants = []
if 0 < self.dropout_U < 1:
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, self.output_dim))
B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
constants.append(B_U)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
if 0 < self.dropout_W < 1:
input_shape = self.input_spec[0].shape
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, input_dim))
B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
constants.append(B_W)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
return constants
Example #11
| Source File: recurrent.py From keras_bn_library with MIT License | 6 votes |
|
def get_constants(self, x): constants = [] if 0 < self.dropout_U < 1: ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1))) ones = K.tile(ones, (1, self.input_dim)) B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(4)] constants.append(B_U) else: constants.append([K.cast_to_floatx(1.) for _ in range(4)]) if 0 < self.dropout_W < 1: input_shape = K.int_shape(x) input_dim = input_shape[-1] ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1))) ones = K.tile(ones, (1, int(input_dim))) B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(4)] constants.append(B_W) else: constants.append([K.cast_to_floatx(1.) for _ in range(4)]) return constants
Example #12
| Source File: dagmm.py From AnomalyDetectionTransformations with MIT License | 6 votes |
|
def call(self, inputs, training=None):
z, gamma_k = inputs
gamma_k_sum = K.sum(gamma_k)
est_phi = K.mean(gamma_k, axis=0)
est_mu = K.dot(K.transpose(gamma_k), z) / gamma_k_sum
est_sigma = K.dot(K.transpose(z - est_mu),
gamma_k * (z - est_mu)) / gamma_k_sum
est_sigma = est_sigma + (K.random_normal(shape=(K.int_shape(z)[1], 1), mean=1e-3, stddev=1e-4) * K.eye(K.int_shape(z)[1]))
self.add_update(K.update(self.phi, est_phi), inputs)
self.add_update(K.update(self.mu, est_mu), inputs)
self.add_update(K.update(self.sigma, est_sigma), inputs)
est_sigma_diag_inv = K.eye(K.int_shape(self.sigma)[0]) / est_sigma
self.add_loss(self.lambd_diag * K.sum(est_sigma_diag_inv), inputs)
phi = K.in_train_phase(est_phi, self.phi, training)
mu = K.in_train_phase(est_mu, self.mu, training)
sigma = K.in_train_phase(est_sigma, self.sigma, training)
return GaussianMixtureComponent._calc_component_density(z, phi, mu, sigma)
Example #13
| Source File: layer.py From SpectralNet with MIT License | 6 votes |
|
def Orthonorm(x, name=None):
'''
Builds keras layer that handles orthogonalization of x
x: an n x d input matrix
name: name of the keras layer
returns: a keras layer instance. during evaluation, the instance returns an n x d orthogonal matrix
if x is full rank and not singular
'''
# get dimensionality of x
d = x.get_shape().as_list()[-1]
# compute orthogonalizing matrix
ortho_weights = orthonorm_op(x)
# create variable that holds this matrix
ortho_weights_store = K.variable(np.zeros((d,d)))
# create op that saves matrix into variable
ortho_weights_update = tf.assign(ortho_weights_store, ortho_weights, name='ortho_weights_update')
# switch between stored and calculated weights based on training or validation
l = Lambda(lambda x: K.in_train_phase(K.dot(x, ortho_weights), K.dot(x, ortho_weights_store)), name=name)
l.add_update(ortho_weights_update)
return l
Example #14
| Source File: rtn.py From ikelos with MIT License | 6 votes |
|
def get_constants(self, x):
constants = []
if 0 < self.dropout_U < 1:
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.concatenate([ones] * self.output_dim, 1)
B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
constants.append(B_U)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
if 0 < self.dropout_W < 1:
input_shape = self.input_spec[0].shape
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.concatenate([ones] * input_dim, 1)
B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
constants.append(B_W)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
return constants
Example #15
| Source File: qrnn.py From embedding-as-service with MIT License | 6 votes |
|
def preprocess_input(self, inputs, training=None):
if self.window_size > 1:
inputs = K.temporal_padding(inputs, (self.window_size - 1, 0))
inputs = K.expand_dims(inputs, 2) # add a dummy dimension
output = K.conv2d(inputs, self.kernel, strides=self.strides,
padding='valid',
data_format='channels_last')
output = K.squeeze(output, 2) # remove the dummy dimension
if self.use_bias:
output = K.bias_add(output, self.bias, data_format='channels_last')
if self.dropout is not None and 0. < self.dropout < 1.:
z = output[:, :, :self.units]
f = output[:, :, self.units:2 * self.units]
o = output[:, :, 2 * self.units:]
f = K.in_train_phase(1 - _dropout(1 - f, self.dropout), f, training=training)
return K.concatenate([z, f, o], -1)
else:
return output
Example #16
| Source File: rtn.py From ikelos with MIT License | 6 votes |
|
def get_constants(self, x):
constants = []
if 0 < self.dropout_U < 1:
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.concatenate([ones] * self.output_dim, 1)
B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(4)]
constants.append(B_U)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(4)])
if 0 < self.dropout_W < 1:
input_shape = self.input_spec[0].shape
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.concatenate([ones] * input_dim, 1)
B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(4)]
constants.append(B_W)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(4)])
return constants
Example #17
| Source File: attention_decoder.py From keras-monotonic-attention with GNU Affero General Public License v3.0 | 6 votes |
|
def _compute_probabilities(self, energy, previous_attention=None):
if self.is_monotonic:
# add presigmoid noise to encourage discreteness
sigmoid_noise = K.in_train_phase(1., 0.)
noise = K.random_normal(K.shape(energy), mean=0.0, stddev=sigmoid_noise)
# encourage discreteness in train
energy = K.in_train_phase(energy + noise, energy)
p = K.in_train_phase(K.sigmoid(energy),
K.cast(energy > 0, energy.dtype))
p = K.squeeze(p, -1)
p_prev = K.squeeze(previous_attention, -1)
# monotonic attention function from tensorflow
at = K.in_train_phase(
tf.contrib.seq2seq.monotonic_attention(p, p_prev, 'parallel'),
tf.contrib.seq2seq.monotonic_attention(p, p_prev, 'hard'))
at = K.expand_dims(at, -1)
else:
# softmax
at = keras.activations.softmax(energy, axis=1)
return at
Example #18
| Source File: crf.py From keras-contrib with MIT License | 6 votes |
|
def call(self, X, mask=None):
if mask is not None:
assert K.ndim(mask) == 2, 'Input mask to CRF must have dim 2 if not None'
if self.test_mode == 'viterbi':
test_output = self.viterbi_decoding(X, mask)
else:
test_output = self.get_marginal_prob(X, mask)
self.uses_learning_phase = True
if self.learn_mode == 'join':
train_output = K.zeros_like(K.dot(X, self.kernel))
out = K.in_train_phase(train_output, test_output)
else:
if self.test_mode == 'viterbi':
train_output = self.get_marginal_prob(X, mask)
out = K.in_train_phase(train_output, test_output)
else:
out = test_output
return out
Example #19
| Source File: decaying_dropout_layer.py From MatchZoo with Apache License 2.0 | 6 votes |
|
def call(self, inputs, training=None):
"""
The computation logic of DecayingDropoutLayer.
:param inputs: an input tensor.
"""
noise_shape = self._get_noise_shape(inputs)
t = tf.cast(self._iterations, K.floatx()) + 1
p = t / float(self._decay_interval)
keep_rate = self._initial_keep_rate * tf.pow(self._decay_rate, p)
def dropped_inputs():
update_op = self._iterations.assign_add([1])
with tf.control_dependencies([update_op]):
return tf.nn.dropout(inputs, 1 - keep_rate[0], noise_shape,
seed=self._seed)
return K.in_train_phase(dropped_inputs, inputs, training=training)
Example #20
| Source File: qrnn.py From nn_playground with MIT License | 6 votes |
|
def preprocess_input(self, inputs, training=None):
if self.window_size > 1:
inputs = K.temporal_padding(inputs, (self.window_size-1, 0))
inputs = K.expand_dims(inputs, 2) # add a dummy dimension
output = K.conv2d(inputs, self.kernel, strides=self.strides,
padding='valid',
data_format='channels_last')
output = K.squeeze(output, 2) # remove the dummy dimension
if self.use_bias:
output = K.bias_add(output, self.bias, data_format='channels_last')
if self.dropout is not None and 0. < self.dropout < 1.:
z = output[:, :, :self.units]
f = output[:, :, self.units:2 * self.units]
o = output[:, :, 2 * self.units:]
f = K.in_train_phase(1 - _dropout(1 - f, self.dropout), f, training=training)
return K.concatenate([z, f, o], -1)
else:
return output
Example #21
| Source File: layers.py From research with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def get_constants(self, x):
constants = []
if 0 < self.dropout_U < 1:
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.concatenate([ones] * self.output_dim, 1)
B_U = K.in_train_phase(K.dropout(ones, self.dropout_U), ones)
constants.append(B_U)
else:
constants.append(K.cast_to_floatx(1.))
if self.consume_less == 'cpu' and 0 < self.dropout_W < 1:
input_shape = self.input_spec[0].shape
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.concatenate([ones] * input_dim, 1)
B_W = K.in_train_phase(K.dropout(ones, self.dropout_W), ones)
constants.append(B_W)
else:
constants.append(K.cast_to_floatx(1.))
return constants
Example #22
| Source File: layers.py From research with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def get_constants(self, x):
constants = []
if 0 < self.dropout_U < 1:
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.concatenate([ones] * self.output_dim, 1)
B_U = K.in_train_phase(K.dropout(ones, self.dropout_U), ones)
constants.append(B_U)
else:
constants.append(K.cast_to_floatx(1.))
if self.consume_less == 'cpu' and 0 < self.dropout_W < 1:
input_shape = self.input_spec[0].shape
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.concatenate([ones] * input_dim, 1)
B_W = K.in_train_phase(K.dropout(ones, self.dropout_W), ones)
constants.append(B_W)
else:
constants.append(K.cast_to_floatx(1.))
return constants
Example #23
| Source File: keras_bert_layer.py From nlp_xiaojiang with MIT License | 6 votes |
|
def call(self, X, mask=None):
if mask is not None:
assert K.ndim(mask) == 2, 'Input mask to CRF must have dim 2 if not None'
if self.test_mode == 'viterbi':
test_output = self.viterbi_decoding(X, mask)
else:
test_output = self.get_marginal_prob(X, mask)
self.uses_learning_phase = True
if self.learn_mode == 'join':
train_output = K.zeros_like(K.dot(X, self.kernel))
out = K.in_train_phase(train_output, test_output)
else:
if self.test_mode == 'viterbi':
train_output = self.get_marginal_prob(X, mask)
out = K.in_train_phase(train_output, test_output)
else:
out = test_output
return out
Example #24
| Source File: layer.py From Deep-Spectral-Clustering-using-Dual-Autoencoder-Network with MIT License | 6 votes |
|
def Orthonorm(x, name=None):
'''
Builds keras layer that handles orthogonalization of x
x: an n x d input matrix
name: name of the keras layer
returns: a keras layer instance. during evaluation, the instance returns an n x d orthogonal matrix
if x is full rank and not singular
'''
# get dimensionality of x
d = x.get_shape().as_list()[-1]
# compute orthogonalizing matrix
ortho_weights = orthonorm_op(x)
# create variable that holds this matrix
ortho_weights_store = K.variable(np.zeros((d,d)))
# create op that saves matrix into variable
ortho_weights_update = tf.assign(ortho_weights_store, ortho_weights, name='ortho_weights_update')
# switch between stored and calculated weights based on training or validation
l = Lambda(lambda x: K.in_train_phase(K.dot(x, ortho_weights), K.dot(x, ortho_weights_store)), name=name)
l.add_update(ortho_weights_update)
return l
Example #25
| Source File: rnnlayer.py From recurrent-attention-for-QA-SQUAD-based-on-keras with MIT License | 6 votes |
|
def get_constants(self, inputs, training=None):
constants = []
'''if 0 < self.dropout_U < 1:
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, self.units))
B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
constants.append(B_U)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
if 0 < self.dropout_W < 1:
input_shape = K.int_shape(x)
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, int(input_dim)))
B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
constants.append(B_W)
else:'''
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
return constants
Example #26
| Source File: rnnlayer.py From recurrent-attention-for-QA-SQUAD-based-on-keras with MIT License | 6 votes |
|
def get_constants(self, inputs, training=None):
constants = []
'''if 0 < self.dropout_U < 1:
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, self.units))
B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
constants.append(B_U)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
if 0 < self.dropout_W < 1:
input_shape = K.int_shape(x)
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, int(input_dim)))
B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
constants.append(B_W)
else:'''
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
return constants
Example #27
| Source File: QnA.py From recurrent-attention-for-QA-SQUAD-based-on-keras with MIT License | 6 votes |
|
def get_constants(self, x):
constants = []
if 0 < self.dropout_U < 1:
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, self.output_dim))
B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
constants.append(B_U)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
if 0 < self.dropout_W < 1:
input_shape = K.int_shape(x)
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, int(input_dim)))
B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
constants.append(B_W)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(3)])
return constants
Example #28
| Source File: layers.py From sequence-tagging-ner with Apache License 2.0 | 6 votes |
|
def call(self, X, mask=None):
if mask is not None:
assert K.ndim(mask) == 2, 'Input mask to CRF must have dim 2 if not None'
if self.test_mode == 'viterbi':
test_output = self.viterbi_decoding(X, mask)
else:
test_output = self.get_marginal_prob(X, mask)
self.uses_learning_phase = True
if self.learn_mode == 'join':
train_output = K.zeros_like(K.dot(X, self.kernel))
out = K.in_train_phase(train_output, test_output)
else:
if self.test_mode == 'viterbi':
train_output = self.get_marginal_prob(X, mask)
out = K.in_train_phase(train_output, test_output)
else:
out = test_output
return out
Example #29
| Source File: TTRNN.py From TT_RNN with MIT License | 5 votes |
|
def get_constants(self, inputs, training=None):
constants = []
if self.implementation != 0 and 0. < self.dropout < 1:
input_shape = K.int_shape(inputs)
input_dim = input_shape[-1]
ones = K.ones_like(K.reshape(inputs[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, int(input_dim)))
def dropped_inputs():
return K.dropout(ones, self.dropout)
dp_mask = [K.in_train_phase(dropped_inputs,
ones,
training=training) for _ in range(4)]
constants.append(dp_mask)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(4)])
if 0. < self.recurrent_dropout < 1:
ones = K.ones_like(K.reshape(inputs[:, 0, 0], (-1, 1)))
ones = K.tile(ones, (1, self.units))
def dropped_inputs():
return K.dropout(ones, self.recurrent_dropout)
rec_dp_mask = [K.in_train_phase(dropped_inputs,
ones,
training=training) for _ in range(4)]
constants.append(rec_dp_mask)
else:
constants.append([K.cast_to_floatx(1.) for _ in range(4)])
return constants
Example #30
| Source File: train.py From Anime-Super-Resolution with MIT License | 5 votes |
|
def mae(self, hr, sr):
margin = (tf.shape(hr)[1] - tf.shape(sr)[1]) // 2
hr_crop = tf.cond(tf.equal(margin, 0), lambda: hr, lambda: hr[:, margin:-margin, margin:-margin, :])
hr = K.in_train_phase(hr_crop, hr)
hr.uses_learning_phase = True
return mean_absolute_error(hr, sr)
