本文整理匯總了Python中tensorflow.truncated_normal_initializer方法的典型用法代碼示例。如果您正苦於以下問題：Python tensorflow.truncated_normal_initializer方法的具體用法？Python tensorflow.truncated_normal_initializer怎麽用？Python tensorflow.truncated_normal_initializer使用的例子？那麽恭喜您, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在模塊tensorflow的用法示例。

在下文中一共展示了tensorflow.truncated_normal_initializer方法的22個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於我們的係統推薦出更棒的Python代碼示例。

示例1: cifarnet_arg_scope

​點讚 6

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def cifarnet_arg_scope(weight_decay=0.004):

"""Defines the default cifarnet argument scope.

Args:

weight_decay: The weight decay to use for regularizing the model.

Returns:

An `arg_scope` to use for the inception v3 model.

"""

with slim.arg_scope(

[slim.conv2d],

weights_initializer=tf.truncated_normal_initializer(stddev=5e-2),

activation_fn=tf.nn.relu):

with slim.arg_scope(

[slim.fully_connected],

biases_initializer=tf.constant_initializer(0.1),

weights_initializer=trunc_normal(0.04),

weights_regularizer=slim.l2_regularizer(weight_decay),

activation_fn=tf.nn.relu) as sc:

return sc

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:22，

示例2: _variable_with_weight_decay

​點讚 6

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def _variable_with_weight_decay(name, shape, stddev, wd):

"""Helper to create an initialized Variable with weight decay.

Note that the Variable is initialized with a truncated normal distribution.

A weight decay is added only if one is specified.

Args:

name: name of the variable

shape: list of ints

stddev: standard deviation of a truncated Gaussian

wd: add L2Loss weight decay multiplied by this float. If None, weight

decay is not added for this Variable.

Returns:

Variable Tensor

"""

dtype = tf.float16 if FLAGS.use_fp16 else tf.float32

var = _variable_on_cpu(

name,

shape,

tf.truncated_normal_initializer(stddev=stddev, dtype=dtype))

if wd is not None:

weight_decay = tf.multiply(tf.nn.l2_loss(var), wd, name='weight_loss')

tf.add_to_collection('losses', weight_decay)

return var

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:27，

示例3: _variable_with_weight_decay

​點讚 6

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def _variable_with_weight_decay(name, shape, stddev, wd):

"""Helper to create an initialized Variable with weight decay.

Note that the Variable is initialized with a truncated normal distribution.

A weight decay is added only if one is specified.

Args:

name: name of the variable

shape: list of ints

stddev: standard deviation of a truncated Gaussian

wd: add L2Loss weight decay multiplied by this float. If None, weight

decay is not added for this Variable.

Returns:

Variable Tensor

"""

var = _variable_on_cpu(name, shape,

tf.truncated_normal_initializer(stddev=stddev))

if wd is not None:

weight_decay = tf.multiply(tf.nn.l2_loss(var), wd, name='weight_loss')

tf.add_to_collection('losses', weight_decay)

return var

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:24，

示例4: _Deconv

​點讚 6

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def _Deconv(self, net, out_filters, kernel_size, stride):

shape = net.get_shape().as_list()

in_filters = shape[3]

kernel_shape = [kernel_size, kernel_size, out_filters, in_filters]

weights = tf.get_variable(

name='weights',

shape=kernel_shape,

dtype=tf.float32,

initializer=tf.truncated_normal_initializer(stddev=0.01))

out_height = shape[1] * stride

out_width = shape[2] * stride

batch_size = shape[0]

output_shape = [batch_size, out_height, out_width, out_filters]

net = tf.nn.conv2d_transpose(net, weights, output_shape,

[1, stride, stride, 1], padding='SAME')

slim.batch_norm(net)

return net

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:23，

示例5: _deconvolutional_layer

​點讚 6

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def _deconvolutional_layer(input, is_training, filters):

# Implements transposed convolutional layers. Returns data with double the shape of input

output = tf.layers.conv2d_transpose(

input,

filters=filters,

kernel_size=(3, 3),

strides=2,

padding='same',

activation=tf.nn.relu,

kernel_initializer=tf.truncated_normal_initializer(stddev=0.1),

kernel_regularizer=tf.contrib.layers.l2_regularizer(0.001)

)

#output = tf.layers.batch_normalization(output, training=is_training)

output = tf.layers.conv2d_transpose(

output,

filters=filters,

kernel_size=(3, 3),

strides=2,

padding='same',

activation=tf.nn.relu,

kernel_initializer=tf.truncated_normal_initializer(stddev=0.1),

kernel_regularizer=tf.contrib.layers.l2_regularizer(0.001)

)

#output = tf.layers.batch_normalization(output, training=is_training)

return output

開發者ID:MaxSobolMark，項目名稱:HardRLWithYoutube，代碼行數:27，

示例6: _convolutional_layer

​點讚 6

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def _convolutional_layer(input, filters, strides, is_training):

"""Constructs a conv2d layer followed by batch normalization, and max pooling"""

x = tf.layers.conv2d(

input,

filters=filters,

kernel_size=(3, 3),

strides=strides,

padding='same',

activation=tf.nn.relu,

kernel_initializer=tf.truncated_normal_initializer(stddev=0.1),

kernel_regularizer=tf.contrib.layers.l2_regularizer(0.001)

)

x = tf.layers.batch_normalization(x, training=is_training)

output = tf.layers.max_pooling2d(x, 2, 2)

return output

開發者ID:MaxSobolMark，項目名稱:HardRLWithYoutube，代碼行數:20，

示例7: M_step

​點讚 6

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def M_step(log_R, log_activation, vote, lambda_val=0.01):

R_shape = tf.shape(log_R)

log_R = log_R + log_activation

R_sum_i = cl.reduce_sum(tf.exp(log_R), axis=-3, keepdims=True)

log_normalized_R = log_R - tf.reduce_logsumexp(log_R, axis=-3, keepdims=True)

pose = cl.reduce_sum(vote * tf.exp(log_normalized_R), axis=-3, keepdims=True)

log_var = tf.reduce_logsumexp(log_normalized_R + cl.log(tf.square(vote - pose)), axis=-3, keepdims=True)

beta_v = tf.get_variable('beta_v',

shape=[1 for i in range(len(pose.shape) - 2)] + [pose.shape[-2], 1],

initializer=tf.truncated_normal_initializer(mean=15., stddev=3.))

cost = R_sum_i * (beta_v + 0.5 * log_var)

beta_a = tf.get_variable('beta_a',

shape=[1 for i in range(len(pose.shape) - 2)] + [pose.shape[-2], 1],

initializer=tf.truncated_normal_initializer(mean=100.0, stddev=10))

cost_sum_h = cl.reduce_sum(cost, axis=-1, keepdims=True)

logit = lambda_val * (beta_a - cost_sum_h)

log_activation = tf.log_sigmoid(logit)

return(pose, log_var, log_activation)

開發者ID:naturomics，項目名稱:CapsLayer，代碼行數:25，

示例8: create_initializer

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def create_initializer(initializer_range=0.02):

"""Creates a `truncated_normal_initializer` with the given range."""

return tf.truncated_normal_initializer(stddev=initializer_range)

開發者ID:Socialbird-AILab，項目名稱:BERT-Classification-Tutorial，代碼行數:5，

示例9: embed

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def embed(inputs, vocab_size, num_units, zero_pad=True, scope="embedding", reuse=None):

'''Embeds a given tensor.

Args:

inputs: A `Tensor` with type `int32` or `int64` containing the ids

to be looked up in `lookup table`.

vocab_size: An int. Vocabulary size.

num_units: An int. Number of embedding hidden units.

zero_pad: A boolean. If True, all the values of the fist row (id 0)

should be constant zeros.

scope: Optional scope for `variable_scope`.

reuse: Boolean, whether to reuse the weights of a previous layer

by the same name.

Returns:

A `Tensor` with one more rank than inputs's. The last dimensionality

should be `num_units`.

'''

with tf.variable_scope(scope, reuse=reuse):

lookup_table = tf.get_variable('lookup_table',

dtype=tf.float32,

shape=[vocab_size, num_units],

initializer=tf.truncated_normal_initializer(mean=0.0, stddev=0.1))

if zero_pad:

lookup_table = tf.concat((tf.zeros(shape=[1, num_units]),

lookup_table[1:, :]), 0)

outputs = tf.nn.embedding_lookup(lookup_table, inputs)

return outputs

開發者ID:Kyubyong，項目名稱:dc_tts，代碼行數:32，

示例10: get_weight_variable

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def get_weight_variable(shape, regularizer):

weights = tf.get_variable(

"weigths", shape, initializer=tf.truncated_normal_initializer(stddev=0.1))

# 如果給出了正則生成函數，加入 losses 集合

if regularizer is not None:

tf.add_to_collection('losses', regularizer(weights))

return weights

# 定義前向傳播

開發者ID:wdxtub，項目名稱:deep-learning-note，代碼行數:13，

示例11: conv_relu

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def conv_relu(inputs, filters, k_size, stride, padding, scope_name):

'''

A method that does convolution + relu on inputs

'''

with tf.compat.v1.variable_scope(scope_name, reuse=tf.compat.v1.AUTO_REUSE) as scope:

in_channels = inputs.shape[-1]

kernel = tf.compat.v1.get_variable('kernel',

[k_size, k_size, in_channels, filters],

initializer=tf.truncated_normal_initializer())

biases = tf.compat.v1.get_variable('biases',

[filters],

initializer=tf.random_normal_initializer())

conv = tf.nn.conv2d(inputs, kernel, strides=[1, stride, stride, 1], padding=padding)

return tf.nn.relu(conv + biases, name=scope.name)

開發者ID:wdxtub，項目名稱:deep-learning-note，代碼行數:16，

示例12: fully_connected

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def fully_connected(inputs, out_dim, scope_name='fc'):

'''

A fully connected linear layer on inputs

'''

with tf.compat.v1.variable_scope(scope_name, reuse=tf.compat.v1.AUTO_REUSE) as scope:

in_dim = inputs.shape[-1]

w = tf.compat.v1.get_variable('weights', [in_dim, out_dim],

initializer=tf.truncated_normal_initializer())

b = tf.compat.v1.get_variable('biases', [out_dim],

initializer=tf.constant_initializer(0.0))

out = tf.matmul(inputs, w) + b

return out

開發者ID:wdxtub，項目名稱:deep-learning-note，代碼行數:14，

示例13: mobilenet_v1_arg_scope

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def mobilenet_v1_arg_scope(is_training=True,

weight_decay=0.00004,

stddev=0.09,

regularize_depthwise=False):

"""Defines the default MobilenetV1 arg scope.

Args:

is_training: Whether or not we're training the model.

weight_decay: The weight decay to use for regularizing the model.

stddev: The standard deviation of the trunctated normal weight initializer.

regularize_depthwise: Whether or not apply regularization on depthwise.

Returns:

An `arg_scope` to use for the mobilenet v1 model.

"""

batch_norm_params = {

'is_training': is_training,

'center': True,

'scale': True,

'decay': 0.9997,

'epsilon': 0.001,

}

# Set weight_decay for weights in Conv and DepthSepConv layers.

weights_init = tf.truncated_normal_initializer(stddev=stddev)

regularizer = tf.contrib.layers.l2_regularizer(weight_decay)

if regularize_depthwise:

depthwise_regularizer = regularizer

else:

depthwise_regularizer = None

with slim.arg_scope([slim.conv2d, slim.separable_conv2d],

weights_initializer=weights_init,

activation_fn=tf.nn.relu6, normalizer_fn=slim.batch_norm):

with slim.arg_scope([slim.batch_norm], **batch_norm_params):

with slim.arg_scope([slim.conv2d], weights_regularizer=regularizer):

with slim.arg_scope([slim.separable_conv2d],

weights_regularizer=depthwise_regularizer) as sc:

return sc

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:40，

示例14: lenet_arg_scope

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def lenet_arg_scope(weight_decay=0.0):

"""Defines the default lenet argument scope.

Args:

weight_decay: The weight decay to use for regularizing the model.

Returns:

An `arg_scope` to use for the inception v3 model.

"""

with slim.arg_scope(

[slim.conv2d, slim.fully_connected],

weights_regularizer=slim.l2_regularizer(weight_decay),

weights_initializer=tf.truncated_normal_initializer(stddev=0.1),

activation_fn=tf.nn.relu) as sc:

return sc

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:17，

示例15: __init__

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def __init__(self, image_size, num_channels, hidden_dim):

self.image_size = image_size

self.num_channels = num_channels

self.hidden_dim = hidden_dim

self.matrix_init = tf.truncated_normal_initializer(stddev=0.1)

self.vector_init = tf.constant_initializer(0.0)

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:8，

示例16: __init__

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def __init__(self, key_dim, memory_size, vocab_size,

choose_k=256, alpha=0.1, correct_in_top=1, age_noise=8.0,

var_cache_device='', nn_device='',

num_hashes=None, num_libraries=None):

super(LSHMemory, self).__init__(

key_dim, memory_size, vocab_size,

choose_k=choose_k, alpha=alpha, correct_in_top=1, age_noise=age_noise,

var_cache_device=var_cache_device, nn_device=nn_device)

self.num_libraries = num_libraries or int(self.choose_k ** 0.5)

self.num_per_hash_slot = max(1, self.choose_k // self.num_libraries)

self.num_hashes = (num_hashes or

int(np.log2(self.memory_size / self.num_per_hash_slot)))

self.num_hashes = min(max(self.num_hashes, 1), 20)

self.num_hash_slots = 2 ** self.num_hashes

# hashing vectors

self.hash_vecs = [

tf.get_variable(

'hash_vecs%d' % i, [self.num_hashes, self.key_dim],

dtype=tf.float32, trainable=False,

initializer=tf.truncated_normal_initializer(0, 1))

for i in xrange(self.num_libraries)]

# map representing which hash slots map to which mem keys

self.hash_slots = [

tf.get_variable(

'hash_slots%d' % i, [self.num_hash_slots, self.num_per_hash_slot],

dtype=tf.int32, trainable=False,

initializer=tf.random_uniform_initializer(maxval=self.memory_size,

dtype=tf.int32))

for i in xrange(self.num_libraries)]

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:34，

示例17: _build_initializer

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def _build_initializer(initializer):

"""Build a tf initializer from config.

Args:

initializer: hyperparams_pb2.Hyperparams.regularizer proto.

Returns:

tf initializer.

Raises:

ValueError: On unknown initializer.

"""

initializer_oneof = initializer.WhichOneof('initializer_oneof')

if initializer_oneof == 'truncated_normal_initializer':

return tf.truncated_normal_initializer(

mean=initializer.truncated_normal_initializer.mean,

stddev=initializer.truncated_normal_initializer.stddev)

if initializer_oneof == 'variance_scaling_initializer':

enum_descriptor = (hyperparams_pb2.VarianceScalingInitializer.

DESCRIPTOR.enum_types_by_name['Mode'])

mode = enum_descriptor.values_by_number[initializer.

variance_scaling_initializer.

mode].name

return slim.variance_scaling_initializer(

factor=initializer.variance_scaling_initializer.factor,

mode=mode,

uniform=initializer.variance_scaling_initializer.uniform)

raise ValueError('Unknown initializer function: {}'.format(

initializer_oneof))

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:31，

示例18: __init__

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def __init__(self, env_spec, internal_dim,

fixed_std=True, recurrent=True,

input_prev_actions=True):

self.env_spec = env_spec

self.internal_dim = internal_dim

self.rnn_state_dim = self.internal_dim

self.fixed_std = fixed_std

self.recurrent = recurrent

self.input_prev_actions = input_prev_actions

self.matrix_init = tf.truncated_normal_initializer(stddev=0.01)

self.vector_init = tf.constant_initializer(0.0)

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:14，

示例19: weightVariable

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def weightVariable(shape,std=1.0,name=None):

# Create a set of weights initialized with truncated normal random values

name = 'weights' if name is None else name

return tf.get_variable(name,shape,initializer=tf.truncated_normal_initializer(stddev=std/math.sqrt(shape[0])))

開發者ID:robb-brown，項目名稱:IntroToDeepLearning，代碼行數:6，

示例20: deconv2d

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def deconv2d(input, output_shape, is_train, info=False, k=3, s=2, stddev=0.01,

activation_fn=tf.nn.relu, norm='batch', name='deconv2d'):

with tf.variable_scope(name):

_ = layers.conv2d_transpose(

input,

num_outputs=output_shape,

weights_initializer=tf.truncated_normal_initializer(stddev=stddev),

biases_initializer=tf.zeros_initializer(),

activation_fn=None,

kernel_size=[k, k], stride=[s, s], padding='SAME'

)

_ = norm_and_act(_, is_train, norm=norm, activation_fn=activation_fn)

if info: print_info(name, _.get_shape().as_list(), activation_fn)

return _

開發者ID:clvrai，項目名稱:SSGAN-Tensorflow，代碼行數:16，

示例21: conv2d

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def conv2d(input, output_shape, is_train, k_h=4, k_w=4, s=2,

stddev=0.02, name="conv2d", activation_fn=lrelu, batch_norm=True):

with tf.variable_scope(name):

w = tf.get_variable('w', [k_h, k_w, input.get_shape()[-1], output_shape],

initializer=tf.truncated_normal_initializer(stddev=stddev))

_ = tf.nn.conv2d(input, w, strides=[1, s, s, 1], padding='SAME')

biases = tf.get_variable('biases', [output_shape],

initializer=tf.constant_initializer(0.0))

_ = tf.reshape(tf.nn.bias_add(_, biases), _.get_shape())

return bn_act(_, is_train, batch_norm=batch_norm, activation_fn=activation_fn)

開發者ID:clvrai，項目名稱:Generative-Latent-Optimization-Tensorflow，代碼行數:15，

示例22: deconv2d

​點讚 5

​

# 需要導入模塊: import tensorflow [as 別名]

# 或者: from tensorflow import truncated_normal_initializer [as 別名]

def deconv2d(input, deconv_info, is_train, name="deconv2d",

stddev=0.02, activation_fn=tf.nn.relu, batch_norm=True):

with tf.variable_scope(name):

output_shape = deconv_info[0]

k = deconv_info[1]

s = deconv_info[2]

_ = layers.conv2d_transpose(

input,

num_outputs=output_shape,

weights_initializer=tf.truncated_normal_initializer(stddev=stddev),

biases_initializer=tf.zeros_initializer(),

kernel_size=[k, k], stride=[s, s], padding='SAME'

)

return bn_act(_, is_train, batch_norm=batch_norm, activation_fn=activation_fn)

開發者ID:clvrai，項目名稱:Generative-Latent-Optimization-Tensorflow，代碼行數:17，

注：本文中的tensorflow.truncated_normal_initializer方法示例整理自Github/MSDocs等源碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。