本文整理汇总了Python中tensorflow.contrib.slim.dropout方法的典型用法代码示例。如果您正苦于以下问题：Python slim.dropout方法的具体用法？Python slim.dropout怎么用？Python slim.dropout使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在模块tensorflow.contrib.slim的用法示例。

在下文中一共展示了slim.dropout方法的19个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Python代码示例。

示例1: AddDropout

​点赞 6

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def AddDropout(self, prev_layer, index):

"""Adds a dropout layer.

Args:

prev_layer: Input tensor.

index: Position in model_str to start parsing

Returns:

Output tensor, end index in model_str.

"""

pattern = re.compile(R'(Do)({\w+})?')

m = pattern.match(self.model_str, index)

if m is None:

return None, None

name = self._GetLayerName(m.group(0), index, m.group(2))

layer = slim.dropout(

prev_layer, 0.5, is_training=self.is_training, scope=name)

return layer, m.end()

开发者ID:ringringyi，项目名称:DOTA_models，代码行数:20，

示例2: E

​点赞 6

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def E(self, images, is_training = False, reuse=False):

if images.get_shape()[3] == 3:

images = tf.image.rgb_to_grayscale(images)

with tf.variable_scope('encoder',reuse=reuse):

with slim.arg_scope([slim.fully_connected], activation_fn=tf.nn.relu):

with slim.arg_scope([slim.conv2d], activation_fn=tf.nn.relu, padding='VALID'):

net = slim.conv2d(images, 64, 5, scope='conv1')

net = slim.max_pool2d(net, 2, stride=2, scope='pool1')

net = slim.conv2d(net, 128, 5, scope='conv2')

net = slim.max_pool2d(net, 2, stride=2, scope='pool2')

net = tf.contrib.layers.flatten(net)

net = slim.fully_connected(net, 1024, activation_fn=tf.nn.relu, scope='fc3')

net = slim.dropout(net, 0.5, is_training=is_training)

net = slim.fully_connected(net, self.hidden_repr_size, activation_fn=tf.tanh,scope='fc4')

# dropout here or not?

#~ net = slim.dropout(net, 0.5, is_training=is_training)

return net

开发者ID:pmorerio，项目名称:minimal-entropy-correlation-alignment，代码行数:21，

示例3: _arg_scope

​点赞 6

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def _arg_scope(self, is_training, reuse=None):

weight_decay = 0.0

keep_probability = 1.0

batch_norm_params = {

'is_training': is_training,

# Decay for the moving averages.

'decay': 0.995,

# epsilon to prevent 0s in variance.

'epsilon': 0.001

}

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

weights_initializer=slim.xavier_initializer_conv2d(uniform=True),

weights_regularizer=slim.l2_regularizer(weight_decay),

normalizer_fn=slim.batch_norm,

normalizer_params=batch_norm_params):

with tf.variable_scope(self._scope, self._scope, reuse=reuse):

with slim.arg_scope([slim.batch_norm, slim.dropout],

is_training=is_training) as sc:

return sc

开发者ID:Sanster，项目名称:tf_ctpn，代码行数:23，

示例4: conv_tower_fn

​点赞 6

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def conv_tower_fn(self, images, is_training=True, reuse=None):

"""Computes convolutional features using the InceptionV3 model.

Args:

images: A tensor of shape [batch_size, height, width, channels].

is_training: whether is training or not.

reuse: whether or not the network and its variables should be reused. To

be able to reuse 'scope' must be given.

Returns:

A tensor of shape [batch_size, OH, OW, N], where OWxOH is resolution of

output feature map and N is number of output features (depends on the

network architecture).

"""

mparams = self._mparams['conv_tower_fn']

logging.debug('Using final_endpoint=%s', mparams.final_endpoint)

with tf.variable_scope('conv_tower_fn/INCE'):

if reuse:

tf.get_variable_scope().reuse_variables()

with slim.arg_scope(inception.inception_v3_arg_scope()):

with slim.arg_scope([slim.batch_norm, slim.dropout],

is_training=is_training):

net, _ = inception.inception_v3_base(

images, final_endpoint=mparams.final_endpoint)

return net

开发者ID:rky0930，项目名称:yolo_v2，代码行数:27，

示例5: mobilenet_v2_arg_scope

​点赞 6

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def mobilenet_v2_arg_scope(weight_decay, is_training=True, depth_multiplier=1.0, regularize_depthwise=False,

dropout_keep_prob=1.0):

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],

activation_fn=tf.nn.relu, normalizer_fn=slim.batch_norm,

normalizer_params={'is_training': is_training, 'center': True, 'scale': True }):

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

with slim.arg_scope([slim.separable_conv2d],

weights_regularizer=depthwise_regularizer, depth_multiplier=depth_multiplier):

with slim.arg_scope([slim.dropout], is_training=is_training, keep_prob=dropout_keep_prob) as sc:

return sc

开发者ID:ohadlights，项目名称:mobilenetv2，代码行数:23，

示例6: argscope

​点赞 6

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def argscope(is_training=None, normalizer_fn=slim.layer_norm):

"""Default TF argscope used for convnet-based grasping models.

Args:

is_training: Whether this argscope is for training or inference.

normalizer_fn: Which conv/fc normalizer to use.

Returns:

Dictionary of argument overrides.

"""

with slim.arg_scope([slim.batch_norm, slim.dropout], is_training=is_training):

with slim.arg_scope(

[slim.conv2d, slim.fully_connected],

weights_initializer=tf.truncated_normal_initializer(stddev=0.01),

activation_fn=tf.nn.relu,

normalizer_fn=normalizer_fn):

with slim.arg_scope(

[slim.conv2d, slim.max_pool2d], stride=2, padding='VALID') as scope:

return scope

开发者ID:google-research，项目名称:tensor2robot，代码行数:20，

示例7: build_predictions

​点赞 6

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def build_predictions(self, net, rois, is_training, initializer, initializer_bbox):

# Crop image ROIs

pool5 = self._crop_pool_layer(net, rois, "pool5")

pool5_flat = slim.flatten(pool5, scope='flatten')

# Fully connected layers

fc6 = slim.fully_connected(pool5_flat, 4096, scope='fc6')

if is_training:

fc6 = slim.dropout(fc6, keep_prob=0.5, is_training=True, scope='dropout6')

fc7 = slim.fully_connected(fc6, 4096, scope='fc7')

if is_training:

fc7 = slim.dropout(fc7, keep_prob=0.5, is_training=True, scope='dropout7')

# Scores and predictions

cls_score = slim.fully_connected(fc7, self._num_classes, weights_initializer=initializer, trainable=is_training, activation_fn=None, scope='cls_score')

cls_prob = self._softmax_layer(cls_score, "cls_prob")

bbox_prediction = slim.fully_connected(fc7, self._num_classes * 4, weights_initializer=initializer_bbox, trainable=is_training, activation_fn=None, scope='bbox_pred')

return cls_score, cls_prob, bbox_prediction

开发者ID:dBeker，项目名称:Faster-RCNN-TensorFlow-Python3，代码行数:23，

示例8: head_to_tail

​点赞 6

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def head_to_tail(self, fc7_H, fc7_O, pool5_SH, pool5_SO, sp, is_training, name):

with slim.arg_scope(resnet_arg_scope(is_training=is_training)):

fc7_SH = tf.reduce_mean(pool5_SH, axis=[1, 2])

fc7_SO = tf.reduce_mean(pool5_SO, axis=[1, 2])

Concat_SH = tf.concat([fc7_H[:self.H_num,:], fc7_SH[:self.H_num,:]], 1)

fc8_SH = slim.fully_connected(Concat_SH, self.num_fc, scope='fc8_SH')

fc8_SH = slim.dropout(fc8_SH, keep_prob=0.5, is_training=is_training, scope='dropout8_SH')

fc9_SH = slim.fully_connected(fc8_SH, self.num_fc, scope='fc9_SH')

fc9_SH = slim.dropout(fc9_SH, keep_prob=0.5, is_training=is_training, scope='dropout9_SH')

Concat_HOS = tf.concat([fc7_H, \

fc7_O, \

fc7_SH,\

fc7_SO, sp], 1)

fc8_HOS = slim.fully_connected(Concat_HOS, self.num_fc, scope='fc8_HOS')

fc8_HOS = slim.dropout(fc8_HOS, keep_prob=0.5, is_training=is_training, scope='dropout8_HOS')

fc9_HOS = slim.fully_connected(fc8_HOS, self.num_fc, scope='fc9_HOS')

fc9_HOS = slim.dropout(fc9_HOS, keep_prob=0.5, is_training=is_training, scope='dropout9_HOS')

return fc9_SH, fc9_HOS

开发者ID:vt-vl-lab，项目名称:iCAN，代码行数:26，

示例9: head_to_tail

​点赞 6

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def head_to_tail(self, fc7_H, fc7_O, pool5_SH, pool5_SO, sp, is_training, name):

with slim.arg_scope(resnet_arg_scope(is_training=is_training)):

fc7_SH = tf.reduce_mean(pool5_SH, axis=[1, 2])

fc7_SO = tf.reduce_mean(pool5_SO, axis=[1, 2])

Concat_SH = tf.concat([fc7_H, fc7_SH], 1)

fc8_SH = slim.fully_connected(Concat_SH, self.num_fc, scope='fc8_SH')

fc8_SH = slim.dropout(fc8_SH, keep_prob=0.5, is_training=is_training, scope='dropout8_SH')

fc9_SH = slim.fully_connected(fc8_SH, self.num_fc, scope='fc9_SH')

fc9_SH = slim.dropout(fc9_SH, keep_prob=0.5, is_training=is_training, scope='dropout9_SH')

Concat_SO = tf.concat([fc7_O, fc7_SO], 1)

fc8_SO = slim.fully_connected(Concat_SO, self.num_fc, scope='fc8_SO')

fc8_SO = slim.dropout(fc8_SO, keep_prob=0.5, is_training=is_training, scope='dropout8_SO')

fc9_SO = slim.fully_connected(fc8_SO, self.num_fc, scope='fc9_SO')

fc9_SO = slim.dropout(fc9_SO, keep_prob=0.5, is_training=is_training, scope='dropout9_SO')

Concat_SHsp = tf.concat([fc7_H, sp], 1)

Concat_SHsp = slim.fully_connected(Concat_SHsp, self.num_fc, scope='Concat_SHsp')

Concat_SHsp = slim.dropout(Concat_SHsp, keep_prob=0.5, is_training=is_training, scope='dropout6_SHsp')

fc7_SHsp = slim.fully_connected(Concat_SHsp, self.num_fc, scope='fc7_SHsp')

fc7_SHsp = slim.dropout(fc7_SHsp, keep_prob=0.5, is_training=is_training, scope='dropout7_SHsp')

return fc9_SH, fc9_SO, fc7_SHsp

开发者ID:vt-vl-lab，项目名称:iCAN，代码行数:27，

示例10: AddDropout

​点赞 6

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def AddDropout(self, prev_layer, index, reuse=None):

"""Adds a dropout layer.

Args:

prev_layer: Input tensor.

index: Position in model_str to start parsing

Returns:

Output tensor, end index in model_str.

"""

pattern = re.compile(R'(Do)({\w+})?')

m = pattern.match(self.model_str, index)

if m is None:

return None, None

name = self._GetLayerName(m.group(0), index, m.group(2))

layer = slim.dropout(

prev_layer, 0.5, is_training=self.is_training, scope=name)

return layer, m.end()

开发者ID:ftramer，项目名称:ad-versarial，代码行数:20，

示例11: fc_network

​点赞 5

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def fc_network(x, neurons, wt_decay, name, num_pred=None, offset=0,

batch_norm_param=None, dropout_ratio=0.0, is_training=None):

if dropout_ratio > 0:

assert(is_training is not None), \

'is_training needs to be defined when trainnig with dropout.'

repr = []

for i, neuron in enumerate(neurons):

init_var = np.sqrt(2.0/neuron)

if batch_norm_param is not None:

x = slim.fully_connected(x, neuron, activation_fn=None,

weights_initializer=tf.random_normal_initializer(stddev=init_var),

weights_regularizer=slim.l2_regularizer(wt_decay),

normalizer_fn=slim.batch_norm,

normalizer_params=batch_norm_param,

biases_initializer=tf.zeros_initializer(),

scope='{:s}_{:d}'.format(name, offset+i))

else:

x = slim.fully_connected(x, neuron, activation_fn=tf.nn.relu,

weights_initializer=tf.random_normal_initializer(stddev=init_var),

weights_regularizer=slim.l2_regularizer(wt_decay),

biases_initializer=tf.zeros_initializer(),

scope='{:s}_{:d}'.format(name, offset+i))

if dropout_ratio > 0:

x = slim.dropout(x, keep_prob=1-dropout_ratio, is_training=is_training,

scope='{:s}_{:d}'.format('dropout_'+name, offset+i))

repr.append(x)

if num_pred is not None:

init_var = np.sqrt(2.0/num_pred)

x = slim.fully_connected(x, num_pred,

weights_regularizer=slim.l2_regularizer(wt_decay),

weights_initializer=tf.random_normal_initializer(stddev=init_var),

biases_initializer=tf.zeros_initializer(),

activation_fn=None,

scope='{:s}_pred'.format(name))

return x, repr

开发者ID:ringringyi，项目名称:DOTA_models，代码行数:39，

示例12: create_inner_block

​点赞 5

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def create_inner_block(

incoming, scope, nonlinearity=tf.nn.elu,

weights_initializer=tf.truncated_normal_initializer(1e-3),

bias_initializer=tf.zeros_initializer(), regularizer=None,

increase_dim=False, summarize_activations=True):

n = incoming.get_shape().as_list()[-1]

stride = 1

if increase_dim:

n *= 2

stride = 2

incoming = slim.conv2d(

incoming, n, [3, 3], stride, activation_fn=nonlinearity, padding="SAME",

normalizer_fn=_batch_norm_fn, weights_initializer=weights_initializer,

biases_initializer=bias_initializer, weights_regularizer=regularizer,

scope=scope + "/1")

if summarize_activations:

tf.summary.histogram(incoming.name + "/activations", incoming)

incoming = slim.dropout(incoming, keep_prob=0.6)

incoming = slim.conv2d(

incoming, n, [3, 3], 1, activation_fn=None, padding="SAME",

normalizer_fn=None, weights_initializer=weights_initializer,

biases_initializer=bias_initializer, weights_regularizer=regularizer,

scope=scope + "/2")

return incoming

开发者ID:nwojke，项目名称:deep_sort，代码行数:29，

示例13: _network_factory

​点赞 5

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def _network_factory(weight_decay=1e-8):

def factory_fn(image, reuse):

with slim.arg_scope([slim.batch_norm, slim.dropout],

is_training=False):

with slim.arg_scope([slim.conv2d, slim.fully_connected,

slim.batch_norm, slim.layer_norm],

reuse=reuse):

features, logits = _create_network(

image, reuse=reuse, weight_decay=weight_decay)

return features, logits

return factory_fn

开发者ID:nwojke，项目名称:deep_sort，代码行数:15，

示例14: dropout

​点赞 5

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def dropout(x,p=0.7):

x=slim.dropout(x,keep_prob=p)

return x

开发者ID:xggIoU，项目名称:centernet_tensorflow_wilderface_voc，代码行数:5，

示例15: inference

​点赞 5

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def inference(images, keep_probability, phase_train=True, bottleneck_layer_size=128, weight_decay=0.0, reuse=None):

batch_norm_params = {

# Decay for the moving averages.

'decay': 0.995,

# epsilon to prevent 0s in variance.

'epsilon': 0.001,

# force in-place updates of mean and variance estimates

'updates_collections': None,

# Moving averages ends up in the trainable variables collection

'variables_collections': [ tf.GraphKeys.TRAINABLE_VARIABLES ],

}

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

weights_initializer=slim.xavier_initializer_conv2d(uniform=True),

weights_regularizer=slim.l2_regularizer(weight_decay),

normalizer_fn=slim.batch_norm,

normalizer_params=batch_norm_params):

with tf.variable_scope('squeezenet', [images], reuse=reuse):

with slim.arg_scope([slim.batch_norm, slim.dropout],

is_training=phase_train):

net = slim.conv2d(images, 96, [7, 7], stride=2, scope='conv1')

net = slim.max_pool2d(net, [3, 3], stride=2, scope='maxpool1')

net = fire_module(net, 16, 64, scope='fire2')

net = fire_module(net, 16, 64, scope='fire3')

net = fire_module(net, 32, 128, scope='fire4')

net = slim.max_pool2d(net, [2, 2], stride=2, scope='maxpool4')

net = fire_module(net, 32, 128, scope='fire5')

net = fire_module(net, 48, 192, scope='fire6')

net = fire_module(net, 48, 192, scope='fire7')

net = fire_module(net, 64, 256, scope='fire8')

net = slim.max_pool2d(net, [3, 3], stride=2, scope='maxpool8')

net = fire_module(net, 64, 256, scope='fire9')

net = slim.dropout(net, keep_probability)

net = slim.conv2d(net, 1000, [1, 1], activation_fn=None, normalizer_fn=None, scope='conv10')

net = slim.avg_pool2d(net, net.get_shape()[1:3], scope='avgpool10')

net = tf.squeeze(net, [1, 2], name='logits')

net = slim.fully_connected(net, bottleneck_layer_size, activation_fn=None,

scope='Bottleneck', reuse=False)

return net, None

开发者ID:GaoangW，项目名称:TNT，代码行数:40，

示例16: _head_to_tail

​点赞 5

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def _head_to_tail(self, pool5, is_training, reuse=None):

with tf.variable_scope(self._scope, self._scope, reuse=reuse):

pool5_flat = slim.flatten(pool5, scope='flatten')

fc6 = slim.fully_connected(pool5_flat, 4096, scope='fc6')

if is_training:

fc6 = slim.dropout(fc6, keep_prob=0.5, is_training=True,

scope='dropout6')

fc7 = slim.fully_connected(fc6, 4096, scope='fc7')

if is_training:

fc7 = slim.dropout(fc7, keep_prob=0.5, is_training=True,

scope='dropout7')

return fc7

开发者ID:wanjinchang，项目名称:SSH-TensorFlow，代码行数:15，

示例17: _head_to_tail

​点赞 5

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def _head_to_tail(self, pool5, is_training, reuse=None):

with tf.variable_scope(self._vgg_scope, self._vgg_scope, reuse=reuse):

pool5_flat = slim.flatten(pool5, scope='flatten')

fc6 = slim.fully_connected(pool5_flat, 4096, scope='fc6')

if is_training:

fc6 = slim.dropout(fc6, keep_prob=0.5, is_training=True,

scope='dropout6')

fc7 = slim.fully_connected(fc6, 4096, scope='fc7')

if is_training:

fc7 = slim.dropout(fc7, keep_prob=0.5, is_training=True,

scope='dropout7')

return fc7

开发者ID:InnerPeace-Wu，项目名称:densecap-tensorflow，代码行数:15，

示例18: dense_prediction_cell_hparams

​点赞 5

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def dense_prediction_cell_hparams():

"""DensePredictionCell HParams.

Returns:

A dictionary of hyper-parameters used for dense prediction cell with keys:

- reduction_size: Integer, the number of output filters for each operation

inside the cell.

- dropout_on_concat_features: Boolean, apply dropout on the concatenated

features or not.

- dropout_on_projection_features: Boolean, apply dropout on the projection

features or not.

- dropout_keep_prob: Float, when `dropout_on_concat_features' or

`dropout_on_projection_features' is True, the `keep_prob` value used

in the dropout operation.

- concat_channels: Integer, the concatenated features will be

channel-reduced to `concat_channels` channels.

- conv_rate_multiplier: Integer, used to multiply the convolution rates.

This is useful in the case when the output_stride is changed from 16

to 8, we need to double the convolution rates correspondingly.

"""

return {

'reduction_size': 256,

'dropout_on_concat_features': True,

'dropout_on_projection_features': False,

'dropout_keep_prob': 0.9,

'concat_channels': 256,

'conv_rate_multiplier': 1,

}

开发者ID:sercant，项目名称:mobile-segmentation，代码行数:30，

示例19: __init__

​点赞 5

​

# 需要导入模块: from tensorflow.contrib import slim [as 别名]

# 或者: from tensorflow.contrib.slim import dropout [as 别名]

def __init__(self, config, images, embedding_size, is_training,

embedding_l2=True, l2_reg_weight=1e-6, reuse=False):

"""Constructor.

Args:

config: A T object holding training config.

images: A 4-D float32 `Tensor` holding images to embed.

embedding_size: Int, the size of the embedding.

is_training: Boolean, whether or not this is a training or inference-time

graph.

embedding_l2: Boolean, whether or not to l2 normalize the embedding.

l2_reg_weight: Float, weight applied to l2 weight regularization.

reuse: Boolean, whether or not we're reusing this graph.

"""

# Pull out all the embedder hyperparameters.

self._config = config

self._embedding_size = embedding_size

self._l2_reg_weight = l2_reg_weight

self._embedding_l2 = embedding_l2

self._is_training = is_training

self._reuse = reuse

# Pull out pretrained hparams.

pretrained_checkpoint = config.pretrained_checkpoint

pretrained_layer = config.pretrained_layer

pretrained_keep_prob = config.dropout.keep_pretrained

# Build pretrained graph.

(pretrained_output,

self._pretrained_variables,

self.init_fn) = self.build_pretrained_graph(

images, pretrained_layer, pretrained_checkpoint, is_training, reuse)

# Optionally drop out the activations.

pretrained_output = slim.dropout(

pretrained_output, keep_prob=pretrained_keep_prob,

is_training=is_training)

self._pretrained_output = pretrained_output

开发者ID:rky0930，项目名称:yolo_v2，代码行数:40，

注：本文中的tensorflow.contrib.slim.dropout方法示例整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。