Python keras.backend 模块，random_uniform_variable() 实例源码
我们从Python开源项目中，提取了以下10个代码示例，用于说明如何使用keras.backend.random_uniform_variable()。
def KerasCost(self,y_true, y_pred):
#create a random subsampling of the target instances for the test set
#This is rarely going to hit the last entry
sample = K.cast(K.round(K.random_uniform_variable(shape=tuple([self.MMDTargetSampleSize]), low=0,
high=self.MMDTargetTrainSize-1)),IntType)
#this is a subset operation (not a very pretty way to do it)
MMDTargetSampleTrain = K.gather(self.MMDTargetTrain,sample)
#do the same for the validation set
sample = K.cast(K.round(K.random_uniform_variable(shape=tuple([self.MMDTargetSampleSize]),
high=self.MMDTargetValidationSize-1)),IntType)
#and the subset operation
MMDTargetSampleValidation = K.gather(self.MMDTargetValidation,sample)
#create the sample based on whether we are in training or validation steps
MMDtargetSample = K.in_train_phase(MMDTargetSampleTrain, MMDTargetSampleValidation)
#return the MMD cost for this subset
ret= self.cost(self.MMDLayer,MMDtargetSample)
#pretty dumb but y_treu has to be in the cost for keras to not barf when cleaning up
ret = ret + 0*K.sum(y_pred)+0*K.sum(y_true)
return ret
def KerasCost(self,MMDtargetSample)
#pretty dumb but y_treu has to be in the cost for keras to not barf when cleaning up
ret = ret + 0*K.sum(y_pred)+0*K.sum(y_true)
return ret
def build(self, input_shape):
if self.W is None:
self.W = K.variable(np.identity(input_shape[0][2]))
elif isinstance(self.W, np.ndarray):
self.W = K.variable(self.W)
else:
raise RuntimeError()
if self.b is None:
self.b = K.random_uniform_variable((input_shape[0][2],), -0.05, 0.05)
elif isinstance(self.b, np.ndarray):
self.b = K.variable(self.b)
else:
raise RuntimeError()
self.trainable_weights = [self.W, self.b]
def _get_initial_sense_priors(shape, rate_range=None, name=None):
# This returns a Keras variable with the initial values all being 0.5.
if rate_range is None:
low, high = 0.01, 0.99
else:
low, high = rate_range
return K.random_uniform_variable(shape, low, high, name=name)
def create_full_matching_layer_f(self, input_dim_a, input_dim_b):
"""Create a full-matching layer of a model."""
inp_a = Input(shape=(input_dim_a, self.hidden_dim,))
inp_b = Input(shape=(input_dim_b,))
W = []
for i in range(self.perspective_num):
wi = K.random_uniform_variable((1, self.hidden_dim), -1.0, 1.0,
seed=self.seed if self.seed is not None else 243)
W.append(wi)
val = np.concatenate((np.zeros((self.max_sequence_length-1,1)), np.ones((1,1))), axis=0)
kcon = K.constant(value=val, dtype='float32')
inp_b_perm = Lambda(lambda x: K.permute_dimensions(x, (0,2,1)))(inp_b)
last_state = Lambda(lambda x: K.permute_dimensions(K.dot(x, kcon),1)))(inp_b_perm)
m = []
for i in range(self.perspective_num):
outp_a = Lambda(lambda x: x * W[i])(inp_a)
outp_last = Lambda(lambda x: x * W[i])(last_state)
outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(outp_a)
outp_last = Lambda(lambda x: K.l2_normalize(x, -1))(outp_last)
outp_last = Lambda(lambda x: K.permute_dimensions(x,1)))(outp_last)
outp = Lambda(lambda x: K.batch_dot(x[0], x[1], axes=[1, 2]))([outp_last, outp_a])
outp = Lambda(lambda x: K.permute_dimensions(x,1)))(outp)
m.append(outp)
if self.perspective_num > 1:
persp = Lambda(lambda x: K.concatenate(x, 2))(m)
else:
persp = m
model = Model(inputs=[inp_a, inp_b], outputs=persp)
return model
def create_full_matching_layer_b(self,
seed=self.seed if self.seed is not None else 243)
W.append(wi)
val = np.concatenate((np.ones((1, 1)), np.zeros((self.max_sequence_length - 1, 1))), 2, 1)))(inp_b)
last_state = Lambda(lambda x: K.permute_dimensions(K.dot(x, 1)))(inp_b_perm)
m = []
for i in range(self.perspective_num):
outp_a = Lambda(lambda x: x * W[i])(inp_a)
outp_last = Lambda(lambda x: x * W[i])(last_state)
outp_a = Lambda(lambda x: K.l2_normalize(x, 1)))(outp_last)
outp = Lambda(lambda x: K.batch_dot(x[0], 1)))(outp)
m.append(outp)
if self.perspective_num > 1:
persp = Lambda(lambda x: K.concatenate(x, outputs=persp)
return model
def create_maxpool_matching_layer(self, input_dim_b):
"""Create a maxpooling-matching layer of a model."""
inp_a = Input(shape=(input_dim_a,
seed=self.seed if self.seed is not None else 243)
W.append(wi)
m = []
for i in range(self.perspective_num):
outp_a = Lambda(lambda x: x * W[i])(inp_a)
outp_b = Lambda(lambda x: x * W[i])(inp_b)
outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(outp_a)
outp_b = Lambda(lambda x: K.l2_normalize(x, -1))(outp_b)
outp_b = Lambda(lambda x: K.permute_dimensions(x,1)))(outp_b)
outp = Lambda(lambda x: K.batch_dot(x[0], 2]))([outp_b,1)))(outp)
outp = Lambda(lambda x: K.max(x, -1, keepdims=True))(outp)
m.append(outp)
if self.perspective_num > 1:
persp = Lambda(lambda x: K.concatenate(x, outputs=persp)
return model
def create_maxatt_matching_layer(self, input_dim_b):
"""Create a max-attentive-matching layer of a model."""
inp_a = Input(shape=(input_dim_a,))
W = []
for i in range(self.perspective_num):
wi = K.random_uniform_variable((1,
seed=self.seed if self.seed is not None else 243)
W.append(wi)
outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(inp_a)
outp_b = Lambda(lambda x: K.l2_normalize(x, -1))(inp_b)
outp_b = Lambda(lambda x: K.permute_dimensions(x, 1)))(outp_b)
alpha = Lambda(lambda x: K.batch_dot(x[0], outp_a])
alpha = Lambda(lambda x: K.one_hot(K.argmax(x, 1), self.max_sequence_length))(alpha)
hmax = Lambda(lambda x: K.batch_dot(x[0], 2]))([alpha, outp_b])
m = []
for i in range(self.perspective_num):
outp_a = Lambda(lambda x: x * W[i])(inp_a)
outp_hmax = Lambda(lambda x: x * W[i])(hmax)
outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(outp_a)
outp_hmax = Lambda(lambda x: K.l2_normalize(x, -1))(outp_hmax)
outp_hmax = Lambda(lambda x: K.permute_dimensions(x, 1)))(outp_hmax)
outp = Lambda(lambda x: K.batch_dot(x[0], 2]))([outp_hmax, outp_a])
val = np.eye(self.max_sequence_length)
kcon = K.constant(value=val, dtype='float32')
outp = Lambda(lambda x: K.sum(x * kcon, outputs=persp)
return model
def create_att_matching_layer(self, input_dim_b):
"""Create an attentive-matching layer of a model."""
inp_a = Input(shape=(input_dim_a,))
w = []
for i in range(self.perspective_num):
wi = K.random_uniform_variable((1,
seed=self.seed if self.seed is not None else 243)
w.append(wi)
outp_a = Lambda(lambda x: K.l2_normalize(x, outp_a])
alpha = Lambda(lambda x: K.l2_normalize(x, 1))(alpha)
hmean = Lambda(lambda x: K.batch_dot(x[0], outp_b])
m = []
for i in range(self.perspective_num):
outp_a = Lambda(lambda x: x * w[i])(inp_a)
outp_hmean = Lambda(lambda x: x * w[i])(hmean)
outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(outp_a)
outp_hmean = Lambda(lambda x: K.l2_normalize(x, -1))(outp_hmean)
outp_hmean = Lambda(lambda x: K.permute_dimensions(x, 1)))(outp_hmean)
outp = Lambda(lambda x: K.batch_dot(x[0], 2]))([outp_hmean, outputs=persp)
return model
def get_coordinates(matrix_shape, input_channels, num_filters, scale=1.0):
"""
Return meshgrid coordinates. Flattened and stacked in columns.
Parameters
----------
matrix_shape : list_like
Shape of the output matrix
scale : float
Range of the coordinate representation (-scale,scale)
Returns
-------
coords : keras tensor
"""
# Generate coordinate data
x = np.arange(matrix_shape[0]) - matrix_shape[0] // 2
y = np.arange(matrix_shape[1]) - matrix_shape[1] // 2
c = np.arange(input_channels) - input_channels // 2
f = np.arange(num_filters) - num_filters // 2
x = x / (x.max() + 1)
y = y / (y.max() + 1)
c = c / (c.max() + 1)
f = f / (f.max() + 1) # to prevent division by zero
x *= scale
y *= scale
c *= scale
f *= scale
# Generate coordinate data
# the sequence in the meshgrid similar to output of generator
F, C, X, Y = np.meshgrid(f, c, x, y)
R = np.sqrt((X**2) + (Y**2) + (C**2) + (F**2))
total_items = np.prod(matrix_shape) * num_filters * input_channels
# Flatten
Y_r = Y.reshape(total_items)
X_r = X.reshape(total_items)
C_r = C.reshape(total_items)
F_r = F.reshape(total_items)
R_r = R.reshape(total_items)
# Random variable
Rand = K.random_uniform_variable(shape=(Y_r.shape[0], high=1)
coordinates = K.variable(value=np.vstack([X_r, Y_r, C_r, F_r, R_r]).T)
# coordinates = K.concatenate([Rand,coordinates],axis=1)
return coordinates
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 [email protected] 举报，一经查实，本站将立刻删除。