当前位置: 首页>>代码示例>>Python>>正文


Python regularizers.l2_regularizer方法代码示例

本文整理汇总了Python中tensorflow.contrib.layers.python.layers.regularizers.l2_regularizer方法的典型用法代码示例。如果您正苦于以下问题:Python regularizers.l2_regularizer方法的具体用法?Python regularizers.l2_regularizer怎么用?Python regularizers.l2_regularizer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tensorflow.contrib.layers.python.layers.regularizers的用法示例。


在下文中一共展示了regularizers.l2_regularizer方法的13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: vgg_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def vgg_arg_scope(weight_decay=0.0005):
  """Defines the VGG arg scope.

  Args:
    weight_decay: The l2 regularization coefficient.

  Returns:
    An arg_scope.
  """
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      activation_fn=nn_ops.relu,
      weights_regularizer=regularizers.l2_regularizer(weight_decay),
      biases_initializer=init_ops.zeros_initializer()):
    with arg_scope([layers.conv2d], padding='SAME') as arg_sc:
      return arg_sc 
开发者ID:MingtaoGuo,项目名称:Chinese-Character-and-Calligraphic-Image-Processing,代码行数:18,代码来源:vgg16.py

示例2: predictron_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def predictron_arg_scope(weight_decay=0.0001,
                         batch_norm_decay=0.997,
                         batch_norm_epsilon=1e-5,
                         batch_norm_scale=True):
  batch_norm_params = {
    'decay': batch_norm_decay,
    'epsilon': batch_norm_epsilon,
    'scale': batch_norm_scale,
    'updates_collections': tf.GraphKeys.UPDATE_OPS,
  }

  # Set weight_decay for weights in Conv and FC layers.
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      weights_regularizer=regularizers.l2_regularizer(weight_decay)):
    with arg_scope(
        [layers.conv2d],
        weights_initializer=initializers.variance_scaling_initializer(),
        activation_fn=None,
        normalizer_fn=layers_lib.batch_norm,
        normalizer_params=batch_norm_params) as sc:
      return sc 
开发者ID:zhongwen,项目名称:predictron,代码行数:24,代码来源:util.py

示例3: vgg_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def vgg_arg_scope(weight_decay=0.0005):
    """Defines the VGG arg scope.

    Args:
      weight_decay: The l2 regularization coefficient.

    Returns:
      An arg_scope.
    """
    with arg_scope(
        [layers.conv2d, layers_lib.fully_connected],
        activation_fn=nn_ops.relu,
        weights_regularizer=regularizers.l2_regularizer(weight_decay),
        biases_initializer=init_ops.zeros_initializer()
    ):
        with arg_scope([layers.conv2d], padding='SAME') as arg_sc:
            return arg_sc 
开发者ID:Sargunan,项目名称:Table-Detection-using-Deep-learning,代码行数:19,代码来源:truncated_vgg.py

示例4: initialise_network

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def initialise_network(self):
        num_classes = self.segmentation_param.num_classes
        w_regularizer = None
        b_regularizer = None
        reg_type = self.net_param.reg_type.lower()
        decay = self.net_param.decay
        if reg_type == 'l2' and decay > 0:
            from tensorflow.contrib.layers.python.layers import regularizers
            w_regularizer = regularizers.l2_regularizer(decay)
            b_regularizer = regularizers.l2_regularizer(decay)
        elif reg_type == 'l1' and decay > 0:
            from tensorflow.contrib.layers.python.layers import regularizers
            w_regularizer = regularizers.l1_regularizer(decay)
            b_regularizer = regularizers.l1_regularizer(decay)

        self.net = ApplicationNetFactory.create(self.net_param.name)(
            num_classes=num_classes,
            w_regularizer=w_regularizer,
            b_regularizer=b_regularizer,
            acti_func=self.net_param.activation_function) 
开发者ID:soltanianzadeh,项目名称:STNeuroNet,代码行数:22,代码来源:segmentation_application.py

示例5: inception_v2_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def inception_v2_arg_scope(weight_decay=0.00004,
                           batch_norm_var_collection='moving_vars'):
  """Defines the default InceptionV2 arg scope.

  Args:
    weight_decay: The weight decay to use for regularizing the model.
    batch_norm_var_collection: The name of the collection for the batch norm
      variables.

  Returns:
    An `arg_scope` to use for the inception v3 model.
  """
  batch_norm_params = {
      # Decay for the moving averages.
      'decay': 0.9997,
      # epsilon to prevent 0s in variance.
      'epsilon': 0.001,
      # collection containing update_ops.
      'updates_collections': ops.GraphKeys.UPDATE_OPS,
      # collection containing the moving mean and moving variance.
      'variables_collections': {
          'beta': None,
          'gamma': None,
          'moving_mean': [batch_norm_var_collection],
          'moving_variance': [batch_norm_var_collection],
      }
  }

  # Set weight_decay for weights in Conv and FC layers.
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      weights_regularizer=regularizers.l2_regularizer(weight_decay)):
    with arg_scope(
        [layers.conv2d],
        weights_initializer=initializers.variance_scaling_initializer(),
        activation_fn=nn_ops.relu,
        normalizer_fn=layers_lib.batch_norm,
        normalizer_params=batch_norm_params) as sc:
      return sc 
开发者ID:MingtaoGuo,项目名称:Chinese-Character-and-Calligraphic-Image-Processing,代码行数:41,代码来源:inception_v2.py

示例6: alexnet_v2_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def alexnet_v2_arg_scope(weight_decay=0.0005):
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      activation_fn=nn_ops.relu,
      biases_initializer=init_ops.constant_initializer(0.1),
      weights_regularizer=regularizers.l2_regularizer(weight_decay)):
    with arg_scope([layers.conv2d], padding='SAME'):
      with arg_scope([layers_lib.max_pool2d], padding='VALID') as arg_sc:
        return arg_sc 
开发者ID:MingtaoGuo,项目名称:Chinese-Character-and-Calligraphic-Image-Processing,代码行数:11,代码来源:alexnet_v2.py

示例7: overfeat_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def overfeat_arg_scope(weight_decay=0.0005):
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      activation_fn=nn_ops.relu,
      weights_regularizer=regularizers.l2_regularizer(weight_decay),
      biases_initializer=init_ops.zeros_initializer()):
    with arg_scope([layers.conv2d], padding='SAME'):
      with arg_scope([layers_lib.max_pool2d], padding='VALID') as arg_sc:
        return arg_sc 
开发者ID:ryfeus,项目名称:lambda-packs,代码行数:11,代码来源:overfeat.py

示例8: resnet_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def resnet_arg_scope(is_training=True,
                     weight_decay=cfg.TRAIN.WEIGHT_DECAY,
                     batch_norm_decay=0.997,
                     batch_norm_epsilon=1e-5,
                     batch_norm_scale=True):
  batch_norm_params = {
    # NOTE 'is_training' here does not work because inside resnet it gets reset:
    # https://github.com/tensorflow/models/blob/master/slim/nets/resnet_v1.py#L187
    'is_training': False,
    'decay': batch_norm_decay,
    'epsilon': batch_norm_epsilon,
    'scale': batch_norm_scale,
    'trainable': cfg.RESNET.BN_TRAIN,
    'updates_collections': ops.GraphKeys.UPDATE_OPS
  }

  with arg_scope(
      [slim.conv2d],
      weights_regularizer=regularizers.l2_regularizer(weight_decay),
      weights_initializer=initializers.variance_scaling_initializer(),
      trainable=is_training,
      activation_fn=nn_ops.relu,
      normalizer_fn=layers.batch_norm,
      normalizer_params=batch_norm_params):
    with arg_scope([layers.batch_norm], **batch_norm_params) as arg_sc:
      return arg_sc 
开发者ID:pengzhou1108,项目名称:RGB-N,代码行数:28,代码来源:resnet_fusion_noise.py

示例9: inception_v1_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def inception_v1_arg_scope(weight_decay=0.00004,
                           use_batch_norm=True,
                           batch_norm_var_collection='moving_vars'):
  """Defines the default InceptionV1 arg scope.

  Note: Althougth the original paper didn't use batch_norm we found it useful.

  Args:
    weight_decay: The weight decay to use for regularizing the model.
    use_batch_norm: "If `True`, batch_norm is applied after each convolution.
    batch_norm_var_collection: The name of the collection for the batch norm
      variables.

  Returns:
    An `arg_scope` to use for the inception v3 model.
  """
  batch_norm_params = {
      # Decay for the moving averages.
      'decay': 0.9997,
      # epsilon to prevent 0s in variance.
      'epsilon': 0.001,
      # collection containing update_ops.
      'updates_collections': ops.GraphKeys.UPDATE_OPS,
      # collection containing the moving mean and moving variance.
      'variables_collections': {
          'beta': None,
          'gamma': None,
          'moving_mean': [batch_norm_var_collection],
          'moving_variance': [batch_norm_var_collection],
      }
  }
  if use_batch_norm:
    normalizer_fn = layers_lib.batch_norm
    normalizer_params = batch_norm_params
  else:
    normalizer_fn = None
    normalizer_params = {}
  # Set weight_decay for weights in Conv and FC layers.
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      weights_regularizer=regularizers.l2_regularizer(weight_decay)):
    with arg_scope(
        [layers.conv2d],
        weights_initializer=initializers.variance_scaling_initializer(),
        activation_fn=nn_ops.relu,
        normalizer_fn=normalizer_fn,
        normalizer_params=normalizer_params) as sc:
      return sc 
开发者ID:ryfeus,项目名称:lambda-packs,代码行数:50,代码来源:inception_v1.py

示例10: resnet_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def resnet_arg_scope(is_training=True,
                     weight_decay=0.0001,
                     batch_norm_decay=0.997,
                     batch_norm_epsilon=1e-5,
                     batch_norm_scale=True):
  """Defines the default ResNet arg scope.

  TODO(gpapan): The batch-normalization related default values above are
    appropriate for use in conjunction with the reference ResNet models
    released at https://github.com/KaimingHe/deep-residual-networks. When
    training ResNets from scratch, they might need to be tuned.

  Args:
    is_training: Whether or not we are training the parameters in the batch
      normalization layers of the model. (deprecated)
    weight_decay: The weight decay to use for regularizing the model.
    batch_norm_decay: The moving average decay when estimating layer activation
      statistics in batch normalization.
    batch_norm_epsilon: Small constant to prevent division by zero when
      normalizing activations by their variance in batch normalization.
    batch_norm_scale: If True, uses an explicit `gamma` multiplier to scale the
      activations in the batch normalization layer.

  Returns:
    An `arg_scope` to use for the resnet models.
  """
  batch_norm_params = {
      'is_training': is_training,
      'decay': batch_norm_decay,
      'epsilon': batch_norm_epsilon,
      'scale': batch_norm_scale,
      'updates_collections': ops.GraphKeys.UPDATE_OPS,
  }

  with arg_scope(
      [layers_lib.conv2d],
      weights_regularizer=regularizers.l2_regularizer(weight_decay),
      weights_initializer=initializers.variance_scaling_initializer(),
      activation_fn=nn_ops.relu,
      normalizer_fn=layers.batch_norm):
    with arg_scope([layers.batch_norm], **batch_norm_params):
      # The following implies padding='SAME' for pool1, which makes feature
      # alignment easier for dense prediction tasks. This is also used in
      # https://github.com/facebook/fb.resnet.torch. However the accompanying
      # code of 'Deep Residual Learning for Image Recognition' uses
      # padding='VALID' for pool1. You can switch to that choice by setting
      # tf.contrib.framework.arg_scope([tf.contrib.layers.max_pool2d], padding='VALID').
      with arg_scope([layers.max_pool2d], padding='SAME') as arg_sc:
        return arg_sc 
开发者ID:ryfeus,项目名称:lambda-packs,代码行数:51,代码来源:resnet_utils.py

示例11: inception_v3_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def inception_v3_arg_scope(weight_decay=0.00004,
                           stddev=0.1,
                           batch_norm_var_collection='moving_vars'):
  """Defines the default InceptionV3 arg scope.

  Args:
    weight_decay: The weight decay to use for regularizing the model.
    stddev: The standard deviation of the trunctated normal weight initializer.
    batch_norm_var_collection: The name of the collection for the batch norm
      variables.

  Returns:
    An `arg_scope` to use for the inception v3 model.
  """
  batch_norm_params = {
      # Decay for the moving averages.
      'decay': 0.9997,
      # epsilon to prevent 0s in variance.
      'epsilon': 0.001,
      # collection containing update_ops.
      'updates_collections': ops.GraphKeys.UPDATE_OPS,
      # collection containing the moving mean and moving variance.
      'variables_collections': {
          'beta': None,
          'gamma': None,
          'moving_mean': [batch_norm_var_collection],
          'moving_variance': [batch_norm_var_collection],
      }
  }

  # Set weight_decay for weights in Conv and FC layers.
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      weights_regularizer=regularizers.l2_regularizer(weight_decay)):
    with arg_scope(
        [layers.conv2d],
        weights_initializer=init_ops.truncated_normal_initializer(
            stddev=stddev),
        activation_fn=nn_ops.relu,
        normalizer_fn=layers_lib.batch_norm,
        normalizer_params=batch_norm_params) as sc:
      return sc 
开发者ID:ryfeus,项目名称:lambda-packs,代码行数:44,代码来源:inception_v3.py

示例12: resnet_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def resnet_arg_scope(is_training=True,
                     weight_decay=0.0001,
                     batch_norm_decay=0.997,
                     batch_norm_epsilon=1e-5,
                     batch_norm_scale=True):
  """Defines the default ResNet arg scope.

  TODO(gpapan): The batch-normalization related default values above are
    appropriate for use in conjunction with the reference ResNet models
    released at https://github.com/KaimingHe/deep-residual-networks. When
    training ResNets from scratch, they might need to be tuned.

  Args:
    is_training: Whether or not we are training the parameters in the batch
      normalization layers of the model.
    weight_decay: The weight decay to use for regularizing the model.
    batch_norm_decay: The moving average decay when estimating layer activation
      statistics in batch normalization.
    batch_norm_epsilon: Small constant to prevent division by zero when
      normalizing activations by their variance in batch normalization.
    batch_norm_scale: If True, uses an explicit `gamma` multiplier to scale the
      activations in the batch normalization layer.

  Returns:
    An `arg_scope` to use for the resnet models.
  """
  batch_norm_params = {
      'is_training': is_training,
      'decay': batch_norm_decay,
      'epsilon': batch_norm_epsilon,
      'scale': batch_norm_scale,
      'updates_collections': ops.GraphKeys.UPDATE_OPS,
  }

  with arg_scope(
      [layers_lib.conv2d],
      weights_regularizer=regularizers.l2_regularizer(weight_decay),
      weights_initializer=initializers.variance_scaling_initializer(),
      activation_fn=nn_ops.relu,
      normalizer_fn=layers.batch_norm,
      normalizer_params=batch_norm_params):
    with arg_scope([layers.batch_norm], **batch_norm_params):
      # The following implies padding='SAME' for pool1, which makes feature
      # alignment easier for dense prediction tasks. This is also used in
      # https://github.com/facebook/fb.resnet.torch. However the accompanying
      # code of 'Deep Residual Learning for Image Recognition' uses
      # padding='VALID' for pool1. You can switch to that choice by setting
      # tf.contrib.framework.arg_scope([tf.contrib.layers.max_pool2d], padding='VALID').
      with arg_scope([layers.max_pool2d], padding='SAME') as arg_sc:
        return arg_sc 
开发者ID:abhisuri97,项目名称:auto-alt-text-lambda-api,代码行数:52,代码来源:resnet_utils.py

示例13: inception_v2_arg_scope

# 需要导入模块: from tensorflow.contrib.layers.python.layers import regularizers [as 别名]
# 或者: from tensorflow.contrib.layers.python.layers.regularizers import l2_regularizer [as 别名]
def inception_v2_arg_scope(weight_decay=0.00004,
                           batch_norm_var_collection='moving_vars',
                           batch_norm_decay=0.9997,
                           batch_norm_epsilon=0.001,
                           updates_collections=ops.GraphKeys.UPDATE_OPS,
                           use_fused_batchnorm=True):
  """Defines the default InceptionV2 arg scope.

  Args:
    weight_decay: The weight decay to use for regularizing the model.
    batch_norm_var_collection: The name of the collection for the batch norm
      variables.
    batch_norm_decay: Decay for batch norm moving average
    batch_norm_epsilon: Small float added to variance to avoid division by zero
    updates_collections: Collections for the update ops of the layer
    use_fused_batchnorm: Enable fused batchnorm.

  Returns:
    An `arg_scope` to use for the inception v3 model.
  """
  batch_norm_params = {
      # Decay for the moving averages.
      'decay': batch_norm_decay,
      # epsilon to prevent 0s in variance.
      'epsilon': batch_norm_epsilon,
      # collection containing update_ops.
      'updates_collections': updates_collections,
      # Enable fused batchnorm.
      'fused': use_fused_batchnorm,
      # collection containing the moving mean and moving variance.
      'variables_collections': {
          'beta': None,
          'gamma': None,
          'moving_mean': [batch_norm_var_collection],
          'moving_variance': [batch_norm_var_collection],
      }
  }

  # Set weight_decay for weights in Conv and FC layers.
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      weights_regularizer=regularizers.l2_regularizer(weight_decay)):
    with arg_scope(
        [layers.conv2d],
        weights_initializer=initializers.variance_scaling_initializer(),
        activation_fn=nn_ops.relu,
        normalizer_fn=layers_lib.batch_norm,
        normalizer_params=batch_norm_params) as sc:
      return sc 
开发者ID:mlperf,项目名称:training_results_v0.5,代码行数:51,代码来源:inception_v2_tpu_model.py


注:本文中的tensorflow.contrib.layers.python.layers.regularizers.l2_regularizer方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,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。