resnet_utils.py 文件源码

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