Python tensorflow.contrib.layers.l1_regularizer() Examples
The following are 7
code examples of tensorflow.contrib.layers.l1_regularizer().
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
tensorflow.contrib.layers
, or try the search function
.
.
Example #1
| Source File: hybrid_model.py From lambda-packs with MIT License | 6 votes |
|
def __init__(self,
params,
device_assigner=None,
optimizer_class=adagrad.AdagradOptimizer,
**kwargs):
self.device_assigner = (
device_assigner or framework_variables.VariableDeviceChooser())
self.params = params
self.optimizer = optimizer_class(self.params.learning_rate)
self.is_regression = params.regression
self.regularizer = None
if params.regularization == "l1":
self.regularizer = layers.l1_regularizer(
self.params.regularization_strength)
elif params.regularization == "l2":
self.regularizer = layers.l2_regularizer(
self.params.regularization_strength)
Example #2
| Source File: hybrid_model.py From auto-alt-text-lambda-api with MIT License | 6 votes |
|
def __init__(self,
params,
device_assigner=None,
optimizer_class=adagrad.AdagradOptimizer,
**kwargs):
self.device_assigner = (
device_assigner or tensor_forest.RandomForestDeviceAssigner())
self.params = params
self.optimizer = optimizer_class(self.params.learning_rate)
self.is_regression = params.regression
self.regularizer = None
if params.regularization == "l1":
self.regularizer = layers.l1_regularizer(
self.params.regularization_strength)
elif params.regularization == "l2":
self.regularizer = layers.l2_regularizer(
self.params.regularization_strength)
Example #3
| Source File: hybrid_model.py From deep_image_model with Apache License 2.0 | 6 votes |
|
def __init__(self,
params,
device_assigner=None,
optimizer_class=adagrad.AdagradOptimizer,
**kwargs):
self.device_assigner = (
device_assigner or tensor_forest.RandomForestDeviceAssigner())
self.params = params
self.optimizer = optimizer_class(self.params.learning_rate)
self.is_regression = params.regression
self.regularizer = None
if params.regularization == "l1":
self.regularizer = layers.l1_regularizer(
self.params.regularization_strength)
elif params.regularization == "l2":
self.regularizer = layers.l2_regularizer(
self.params.regularization_strength)
Example #4
| Source File: hyperparams_builder.py From aster with MIT License | 6 votes |
|
def _build_regularizer(regularizer):
"""Builds a regularizer from config.
Args:
regularizer: hyperparams_pb2.Hyperparams.regularizer proto.
Returns:
regularizer.
Raises:
ValueError: On unknown regularizer.
"""
regularizer_oneof = regularizer.WhichOneof('regularizer_oneof')
if regularizer_oneof == 'l1_regularizer':
return layers.l1_regularizer(scale=float(regularizer.l1_regularizer.weight))
if regularizer_oneof == 'l2_regularizer':
return layers.l2_regularizer(scale=float(regularizer.l2_regularizer.weight))
raise ValueError('Unknown regularizer function: {}'.format(regularizer_oneof))
Example #5
| Source File: hybrid_model.py From keras-lambda with MIT License | 6 votes |
|
def __init__(self,
params,
device_assigner=None,
optimizer_class=adagrad.AdagradOptimizer,
**kwargs):
self.device_assigner = (
device_assigner or tensor_forest.RandomForestDeviceAssigner())
self.params = params
self.optimizer = optimizer_class(self.params.learning_rate)
self.is_regression = params.regression
self.regularizer = None
if params.regularization == "l1":
self.regularizer = layers.l1_regularizer(
self.params.regularization_strength)
elif params.regularization == "l2":
self.regularizer = layers.l2_regularizer(
self.params.regularization_strength)
Example #6
| Source File: nn.py From visual_question_answering with MIT License | 5 votes |
|
def prepare(self):
""" Setup the weight initalizers and regularizers. """
config = self.config
self.conv_kernel_initializer = layers.xavier_initializer()
if self.train_cnn and config.conv_kernel_regularizer_scale > 0:
self.conv_kernel_regularizer = layers.l2_regularizer(
scale = config.conv_kernel_regularizer_scale)
else:
self.conv_kernel_regularizer = None
if self.train_cnn and config.conv_activity_regularizer_scale > 0:
self.conv_activity_regularizer = layers.l1_regularizer(
scale = config.conv_activity_regularizer_scale)
else:
self.conv_activity_regularizer = None
self.fc_kernel_initializer = tf.random_uniform_initializer(
minval = -config.fc_kernel_initializer_scale,
maxval = config.fc_kernel_initializer_scale)
if self.is_train and config.fc_kernel_regularizer_scale > 0:
self.fc_kernel_regularizer = layers.l2_regularizer(
scale = config.fc_kernel_regularizer_scale)
else:
self.fc_kernel_regularizer = None
if self.is_train and config.fc_activity_regularizer_scale > 0:
self.fc_activity_regularizer = layers.l1_regularizer(
scale = config.fc_activity_regularizer_scale)
else:
self.fc_activity_regularizer = None
Example #7
| Source File: nn.py From image_captioning with MIT License | 5 votes |
|
def prepare(self):
""" Setup the weight initalizers and regularizers. """
config = self.config
self.conv_kernel_initializer = layers.xavier_initializer()
if self.train_cnn and config.conv_kernel_regularizer_scale > 0:
self.conv_kernel_regularizer = layers.l2_regularizer(
scale = config.conv_kernel_regularizer_scale)
else:
self.conv_kernel_regularizer = None
if self.train_cnn and config.conv_activity_regularizer_scale > 0:
self.conv_activity_regularizer = layers.l1_regularizer(
scale = config.conv_activity_regularizer_scale)
else:
self.conv_activity_regularizer = None
self.fc_kernel_initializer = tf.random_uniform_initializer(
minval = -config.fc_kernel_initializer_scale,
maxval = config.fc_kernel_initializer_scale)
if self.is_train and config.fc_kernel_regularizer_scale > 0:
self.fc_kernel_regularizer = layers.l2_regularizer(
scale = config.fc_kernel_regularizer_scale)
else:
self.fc_kernel_regularizer = None
if self.is_train and config.fc_activity_regularizer_scale > 0:
self.fc_activity_regularizer = layers.l1_regularizer(
scale = config.fc_activity_regularizer_scale)
else:
self.fc_activity_regularizer = None
