inception_utils.py

# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Contains common code shared by all inception models.

Usage of arg scope:
  with slim.arg_scope(inception_arg_scope()):
    logits, end_points = inception.inception_v3(images, num_classes,
                                                is_training=is_training)

"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import tensorflow.compat.v1 as tf
import tf_slim as slim


def inception_arg_scope(
    weight_decay=0.00004,
    use_batch_norm=True,
    batch_norm_decay=0.9997,
    batch_norm_epsilon=0.001,
    activation_fn=tf.nn.relu,
    batch_norm_updates_collections=tf.GraphKeys.UPDATE_OPS,
    batch_norm_scale=False):
  """Defines the default arg scope for inception models.

  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_decay: Decay for batch norm moving average.
    batch_norm_epsilon: Small float added to variance to avoid dividing by zero
      in batch norm.
    activation_fn: Activation function for conv2d.
    batch_norm_updates_collections: Collection for the update ops for
      batch norm.
    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 inception models.
  """
  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': batch_norm_updates_collections,
      # use fused batch norm if possible.
      'fused': None,
      'scale': batch_norm_scale,
  }
  if use_batch_norm:
    normalizer_fn = slim.batch_norm
    normalizer_params = batch_norm_params
  else:
    normalizer_fn = None
    normalizer_params = {}
  # Set weight_decay for weights in Conv and FC layers.
  with slim.arg_scope([slim.conv2d, slim.fully_connected],
                      weights_regularizer=slim.l2_regularizer(weight_decay)):
    with slim.arg_scope(
        [slim.conv2d],
        weights_initializer=slim.variance_scaling_initializer(),
        activation_fn=activation_fn,
        normalizer_fn=normalizer_fn,
        normalizer_params=normalizer_params) as sc:
      return sc