本文整理汇总了Python中tensorflow.python.layers.core.dropout方法的典型用法代码示例。如果您正苦于以下问题:Python core.dropout方法的具体用法?Python core.dropout怎么用?Python core.dropout使用的例子?那么, 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类tensorflow.python.layers.core
的用法示例。
在下文中一共展示了core.dropout方法的6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,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: dropout
# 需要导入模块: from tensorflow.python.layers import core [as 别名]
# 或者: from tensorflow.python.layers.core import dropout [as 别名]
def dropout(self, keep_prob=0.5, input_layer=None):
if input_layer is None:
input_layer = self.top_layer
else:
self.top_size = None
name = 'dropout' + str(self.counts['dropout'])
with tf.variable_scope(name):
if not self.phase_train:
keep_prob = 1.0
if self.use_tf_layers:
dropout = core_layers.dropout(input_layer, 1. - keep_prob,
training=self.phase_train)
else:
dropout = tf.nn.dropout(input_layer, keep_prob)
self.top_layer = dropout
return dropout
示例2: classifier
# 需要导入模块: from tensorflow.python.layers import core [as 别名]
# 或者: from tensorflow.python.layers.core import dropout [as 别名]
def classifier(x, phase, enc_phase=1, trim=0, scope='class', reuse=None, internal_update=False, getter=None):
with tf.variable_scope(scope, reuse=reuse, custom_getter=getter):
with arg_scope([leaky_relu], a=0.1), \
arg_scope([conv2d, dense], activation=leaky_relu, bn=True, phase=phase), \
arg_scope([batch_norm], internal_update=internal_update):
preprocess = instance_norm if args.inorm else tf.identity
layout = [
(preprocess, (), {}),
(conv2d, (64, 3, 1), {}),
(conv2d, (64, 3, 1), {}),
(conv2d, (64, 3, 1), {}),
(max_pool, (2, 2), {}),
(dropout, (), dict(training=phase)),
(noise, (1,), dict(phase=phase)),
(conv2d, (64, 3, 1), {}),
(conv2d, (64, 3, 1), {}),
(conv2d, (64, 3, 1), {}),
(max_pool, (2, 2), {}),
(dropout, (), dict(training=phase)),
(noise, (1,), dict(phase=phase)),
(conv2d, (64, 3, 1), {}),
(conv2d, (64, 3, 1), {}),
(conv2d, (64, 3, 1), {}),
(avg_pool, (), dict(global_pool=True)),
(dense, (args.Y,), dict(activation=None))
]
if enc_phase:
start = 0
end = len(layout) - trim
else:
start = len(layout) - trim
end = len(layout)
for i in xrange(start, end):
with tf.variable_scope('l{:d}'.format(i)):
f, f_args, f_kwargs = layout[i]
x = f(x, *f_args, **f_kwargs)
return x
示例3: dropout
# 需要导入模块: from tensorflow.python.layers import core [as 别名]
# 或者: from tensorflow.python.layers.core import dropout [as 别名]
def dropout(self, keep_prob=0.5, input_layer=None):
if input_layer is None:
input_layer = self.top_layer
else:
self.top_size = None
name = 'dropout' + str(self.counts['dropout'])
with tf.variable_scope(name):
if not self.phase_train:
keep_prob = 1.0
if self.use_tf_layers:
dropout = core_layers.dropout(input_layer, 1. - keep_prob)
else:
dropout = tf.nn.dropout(input_layer, keep_prob)
self.top_layer = dropout
return dropout
示例4: _dropout
# 需要导入模块: from tensorflow.python.layers import core [as 别名]
# 或者: from tensorflow.python.layers.core import dropout [as 别名]
def _dropout(self, bottom, drop_rate):
return dropout(bottom, rate=drop_rate, training=self.training)
示例5: dropout
# 需要导入模块: from tensorflow.python.layers import core [as 别名]
# 或者: from tensorflow.python.layers.core import dropout [as 别名]
def dropout(self, keep_prob=0.5, input_layer=None):
if input_layer is None:
input_layer = self.top_layer
else:
self.top_size = None
name = 'dropout' + str(self.counts['dropout'])
with tf.variable_scope(name):
if not self.phase_train:
keep_prob = 1.0
if self.use_tf_layers:
dropout = core_layers.dropout(input_layer, 1. - keep_prob)
else:
dropout = tf.nn.dropout(input_layer, keep_prob)
self.top_layer = dropout
return dropout
示例6: __init__
# 需要导入模块: from tensorflow.python.layers import core [as 别名]
# 或者: from tensorflow.python.layers.core import dropout [as 别名]
def __init__(self,
hidden_units,
feature_columns,
model_dir=None,
label_dimension=1,
weight_column=None,
optimizer='Adagrad',
activation_fn=nn.relu,
dropout=None,
input_layer_partitioner=None,
config=None):
"""Initializes a `DNNRegressor` instance.
Args:
hidden_units: Iterable of number hidden units per layer. All layers are
fully connected. Ex. `[64, 32]` means first layer has 64 nodes and
second one has 32.
feature_columns: An iterable containing all the feature columns used by
the model. All items in the set should be instances of classes derived
from `_FeatureColumn`.
model_dir: Directory to save model parameters, graph and etc. This can
also be used to load checkpoints from the directory into a estimator to
continue training a previously saved model.
label_dimension: Number of regression targets per example. This is the
size of the last dimension of the labels and logits `Tensor` objects
(typically, these have shape `[batch_size, label_dimension]`).
weight_column: A string or a `_NumericColumn` created by
`tf.feature_column.numeric_column` defining feature column representing
weights. It is used to down weight or boost examples during training. It
will be multiplied by the loss of the example. If it is a string, it is
used as a key to fetch weight tensor from the `features`. If it is a
`_NumericColumn`, raw tensor is fetched by key `weight_column.key`,
then weight_column.normalizer_fn is applied on it to get weight tensor.
optimizer: An instance of `tf.Optimizer` used to train the model. Defaults
to Adagrad optimizer.
activation_fn: Activation function applied to each layer. If `None`, will
use `tf.nn.relu`.
dropout: When not `None`, the probability we will drop out a given
coordinate.
input_layer_partitioner: Optional. Partitioner for input layer. Defaults
to `min_max_variable_partitioner` with `min_slice_size` 64 << 20.
config: `RunConfig` object to configure the runtime settings.
"""
def _model_fn(features, labels, mode, config):
return _dnn_model_fn(
features=features,
labels=labels,
mode=mode,
head=head_lib. # pylint: disable=protected-access
_regression_head_with_mean_squared_error_loss(
label_dimension=label_dimension, weight_column=weight_column),
hidden_units=hidden_units,
feature_columns=tuple(feature_columns or []),
optimizer=optimizer,
activation_fn=activation_fn,
dropout=dropout,
input_layer_partitioner=input_layer_partitioner,
config=config)
super(DNNRegressor, self).__init__(
model_fn=_model_fn, model_dir=model_dir, config=config)
开发者ID:PacktPublishing,项目名称:Serverless-Deep-Learning-with-TensorFlow-and-AWS-Lambda,代码行数:62,代码来源:dnn.py