tensorflow实战——Tensorflow实现ResNet

#%%
# 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.
# ==============================================================================
"""

Typical use:

   from tensorflow.contrib.slim.nets import resnet_v2

ResNet-101 for image classification into 1000 classes:

   # inputs has shape [batch, 224, 224, 3]
   with slim.arg_scope(resnet_v2.resnet_arg_scope(is_training)):
      net, end_points = resnet_v2.resnet_v2_101(inputs, 1000)

ResNet-101 for semantic segmentation into 21 classes:

   # inputs has shape [batch, 513, 513, 3]
   with slim.arg_scope(resnet_v2.resnet_arg_scope(is_training)):
      net, end_points = resnet_v2.resnet_v2_101(inputs,
                                                21,
                                                global_pool=False,
                                                output_stride=16)
"""
import collections
import tensorflow as tf
slim = tf.contrib.slim


#使用collections.namedtuple设计ResNet基本Block模块组的name tuple(元组),
#但只包含数据结构，不包含具体方法

class Block(collections.namedtuple('Block', ['scope', 'unit_fn', 'args'])):
  """A named tuple describing a ResNet block.

  Its parts are:
    scope: The scope of the `Block`.
    unit_fn: The ResNet unit function which takes as input a `Tensor` and
      returns another `Tensor` with the output of the ResNet unit.
    args: A list of length equal to the number of units in the `Block`. The list
      contains one (depth, depth_bottleneck, stride) tuple for each unit in the
      block to serve as argument to unit_fn.
  """

#降采样的方法
#factor:采样因子
def subsample(inputs, factor, scope=None):
  """Subsamples the input along the spatial dimensions.

  Args:
    inputs: A `Tensor` of size [batch, height_in, width_in, channels].
    factor: The subsampling factor.
    scope: Optional variable_scope.

  Returns:
    output: A `Tensor` of size [batch, height_out, width_out, channels] with the
      input, either intact (if factor == 1) or subsampled (if factor > 1).
  """
  if factor == 1:
    return inputs
  else:
  	#使用最大池化来实现
    return slim.max_pool2d(inputs, [1, 1], stride=factor, scope=scope)

#创建卷积层
def conv2d_same(inputs, num_outputs, kernel_size, stride, scope=None):
  """Strided 2-D convolution with 'SAME' padding.

  When stride > 1, then we do explicit zero-padding, followed by conv2d with
  'VALID' padding.

  Note that

     net = conv2d_same(inputs, num_outputs, 3, stride=stride)

  is equivalent to

     net = slim.conv2d(inputs, num_outputs, 3, stride=1, padding='SAME')
     net = subsample(net, factor=stride)

  whereas

     net = slim.conv2d(inputs, num_outputs, 3, stride=stride, padding='SAME')

  is different when the input's height or width is even, which is why we add the
  current function. For more details, see ResnetUtilsTest.testConv2DSameEven().

  Args:
    inputs: A 4-D tensor of size [batch, height_in, width_in, channels].
    num_outputs: An integer, the number of output filters.
    kernel_size: An int with the kernel_size of the filters.