tensorflow文档中vgg.py解读

文档地址：

https://github.com/tensorflow/models/blob/master/research/slim/nets/vgg.py

vgg 网络结构表：

注：ABCDE 是 5个网络 大题上一样 不同就是网络的层数 即深度不同

LRN是局部相应归一化的操作 现在基本不用

 

开头注释 

​
# 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.
# ==============================================================================

论文基本信息 地址 日期等

"""Contains model definitions for versions of the Oxford VGG network.
These model definitions were introduced in the following technical report:
  Very Deep Convolutional Networks For Large-Scale Image Recognition
  Karen Simonyan and Andrew Zisserman
  arXiv technical report, 2015 
  PDF: http://arxiv.org/pdf/1409.1556.pdf 
  ILSVRC 2014 Slides: http://www.robots.ox.ac.uk/~karen/pdf/ILSVRC_2014.pdf
  CC-BY-4.0
More information can be obtained from the VGG website:
www.robots.ox.ac.uk/~vgg/research/very_deep/

Usage:
  with slim.arg_scope(vgg.vgg_arg_scope()):
    outputs, end_points = vgg.vgg_a(inputs)
  with slim.arg_scope(vgg.vgg_arg_scope()):
    outputs, end_points = vgg.vgg_16(inputs)
@@vgg_a
@@vgg_16
@@vgg_19

 使Python2和Python3版本兼容

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

 导入tensorflow 和slim

import tensorflow as tf

slim = tf.contrib.slim

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 slim.arg_scope([slim.conv2d, slim.fully_connected],
                      activation_fn=tf.nn.relu,
                      weights_regularizer=slim.l2_regularizer(weight_decay),
                      biases_initializer=tf.zeros_initializer()):
    with slim.arg_scope([slim.conv2d], padding='SAME') as arg_sc:
      return arg_sc

 vgg a的定义

#vgg a网络的定义
#参数num_classes分类数 默认1000 is_training：是否使用dropout 默认：是
# dropout_keep_prob=0.5(默认) 以0.5概率丢失特征 等为0.6时 则丢弃的概率是0.4
#spatial_squeeze 空间压缩 默认是
# scope ：每个模型都有自己的scope name 防止混淆
#fc_conv_padding：padding方式 默认VALID
#global_pool 全局平均池化 
def vgg_a(inputs,
          num_classes=1000,
          is_training=True,
          dropout_keep_prob=0.5,
          spatial_squeeze=True,
          scope='vgg_a',
          fc_conv_padding='VALID',
          global_pool=False):
  with tf.variable_scope(scope, 'vgg_a', [inputs]) as sc:
    end_points_collection = sc.original_name_scope + '_end_points'#end_points_collection 用于收集网络的一些权重信息
    # Collect outputs for conv2d, fully_connected and max_pool2d.
    with slim.arg_scope([slim.conv2d, slim.max_pool2d],
                        outputs_collections=end_points_collection):#end_points_collection 记录卷积和池化的权重
      #定义网络的结构
      net = slim.repeat(inputs, 1, slim.conv2d, 64, [3, 3], scope='conv1')#使用这个卷积一次
      net = slim.max_pool2d(net, [2, 2], scope='pool1')
      net = slim.repeat(net, 1, slim.conv2d, 128, [3, 3], scope='conv2')
      net = slim.max_pool2d(net, [2, 2], scope='pool2')
      net = slim.repeat(net, 2, slim.conv2d, 256, [3, 3], scope='conv3')#使用这个卷积两次
      net = slim.max_pool2d(net, [2, 2], scope='pool3')
      net = slim.repeat(net, 2, slim.conv2d, 512, [3, 3], scope='conv4')
      net = slim.max_pool2d(net, [2, 2], scope='pool4')
      net = slim.repeat(net, 2, slim.conv2d, 512, [3, 3], scope='conv5')
      net = slim.max_pool2d(net, [2, 2], scope='pool5')
      #使用卷积的方式来替代全连接  可使网络在一定范围内适应任意尺度图片的输入
      # Use conv2d instead of fully_connected layers.
      net = slim.conv2d(net, 4096, [7, 7], padding=fc_conv_padding, scope='fc6')#把图像尺寸变成1*1*4096
      net = slim.dropout(net, dropout_keep_prob, is_training=is_training,#dropout操作
                         scope='dropout6')
      net = slim.conv2d(net, 4096, [1, 1], scope='fc7') #第二个全连接层
      # Convert end_points_collection into a end_point dict.
      end_points = slim.utils.convert_collection_to_dict(end_points_collection)
      #这个网络标准输入是224*224
      # 当网络图片的输入不是标准输入的时候 我们使用类似于average_global_pooling的操作 在1，2维度上求平均
      if global_pool:
        net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool')
        end_points['global_pool'] = net
      #分类数
      if num_classes:
        net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
                           scope='dropout7')
        net = slim.conv2d(net, num_classes, [1, 1],#这个全连接的输出是分类的个数
                          activation_fn=None,
                          normalizer_fn=None,
                          scope='fc8')
        #到这网络输出是1*1*num_classes 三维
        #有时我们可能需要把其转换为一维的结构就用spatial_squeeze
        #一个维度num_classes
        if spatial_squeeze:
          net = tf.squeeze(net, [1, 2], name='fc8/squeezed')
        end_points[sc.name + '/fc8'] = net
      return net, end_points
vgg_a.default_image_size = 224

 vgg a参数英文解释:

#参数介绍英文
  """Oxford Net VGG 11-Layers version A Example.
  Note: All the fully_connected layers have been transformed to conv2d layers.
        To use in classification mode, resize input to 224x224.
  Args:
    inputs: a tensor of size [batch_size, height, width, channels].
    num_classes: number of predicted classes. If 0 or None, the logits layer is
      omitted and the input features to the logits layer are returned instead.
    is_training: whether or not the model is being trained.
    dropout_keep_prob: the probability that activations are kept in the dropout
      layers during training.
    spatial_squeeze: whether or not should squeeze the spatial dimensions of the
      outputs. Useful to remove unnecessary dimensions for classification.
    scope: Optional scope for the variables.
    fc_conv_padding: the type of padding to use for the fully connected layer
      that is implemented as a convolutional layer. Use 'SAME' padding if you
      are applying the network in a fully convolutional manner and want to
      get a prediction map downsampled by a factor of 32 as an output.
      Otherwise, the output prediction map will be (input / 32) - 6 in case of
      'VALID' padding.
    global_pool: Optional boolean flag. If True, the input to the classification
      layer is avgpooled to size 1x1, for any input size. (This is not part
      of the original VGG architecture.)
  Returns:
    net: the output of the logits layer (if num_classes is a non-zero integer),
      or the input to the logits layer (if num_classes is 0 or None).
    end_points: a dict of tensors with intermediate activations.
  """

vgg 16 和 vgg 19的定义大题相似就是网络结构 不太一样 ：卷积repeat 次数

vgg 16 

def vgg_16(inputs,
           num_classes=1000,
           is_training=True,
           dropout_keep_prob=0.5,
           spatial_squeeze=True,
           scope='vgg_16',
           fc_conv_padding='VALID',
           global_pool=False):
  """Oxford Net VGG 16-Layers version D Example.
  Note: All the fully_connected layers have been transformed to conv2d layers.
        To use in classification mode, resize input to 224x224.
  Args:
    inputs: a tensor of size [batch_size, height, width, channels].
    num_classes: number of predicted classes. If 0 or None, the logits layer is
      omitted and the input features to the logits layer are returned instead.
    is_training: whether or not the model is being trained.
    dropout_keep_prob: the probability that activations are kept in the dropout
      layers during training.
    spatial_squeeze: whether or not should squeeze the spatial dimensions of the
      outputs. Useful to remove unnecessary dimensions for classification.
    scope: Optional scope for the variables.
    fc_conv_padding: the type of padding to use for the fully connected layer
      that is implemented as a convolutional layer. Use 'SAME' padding if you
      are applying the network in a fully convolutional manner and want to
      get a prediction map downsampled by a factor of 32 as an output.
      Otherwise, the output prediction map will be (input / 32) - 6 in case of
      'VALID' padding.
    global_pool: Optional boolean flag. If True, the input to the classification
      layer is avgpooled to size 1x1, for any input size. (This is not part
      of the original VGG architecture.)
  Returns:
    net: the output of the logits layer (if num_classes is a non-zero integer),
      or the input to the logits layer (if num_classes is 0 or None).
    end_points: a dict of tensors with intermediate activations.
  """
  with tf.variable_scope(scope, 'vgg_16', [inputs]) as sc:
    end_points_collection = sc.original_name_scope + '_end_points'
    # Collect outputs for conv2d, fully_connected and max_pool2d.
    with slim.arg_scope([slim.conv2d, slim.fully_connected, slim.max_pool2d],
                        outputs_collections=end_points_collection):
      net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
      net = slim.max_pool2d(net, [2, 2], scope='pool1')
      net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
      net = slim.max_pool2d(net, [2, 2], scope='pool2')
      net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')
      net = slim.max_pool2d(net, [2, 2], scope='pool3')
      net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4')
      net = slim.max_pool2d(net, [2, 2], scope='pool4')
      net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
      net = slim.max_pool2d(net, [2, 2], scope='pool5')

      # Use conv2d instead of fully_connected layers.
      net = slim.conv2d(net, 4096, [7, 7], padding=fc_conv_padding, scope='fc6')
      net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
                         scope='dropout6')
      net = slim.conv2d(net, 4096, [1, 1], scope='fc7')
      # Convert end_points_collection into a end_point dict.
      end_points = slim.utils.convert_collection_to_dict(end_points_collection)
      if global_pool:
        net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool')
        end_points['global_pool'] = net
      if num_classes:
        net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
                           scope='dropout7')
        net = slim.conv2d(net, num_classes, [1, 1],
                          activation_fn=None,
                          normalizer_fn=None,
                          scope='fc8')
        if spatial_squeeze:
          net = tf.squeeze(net, [1, 2], name='fc8/squeezed')
        end_points[sc.name + '/fc8'] = net
      return net, end_points
vgg_16.default_image_size = 224

vgg 19 

def vgg_19(inputs,
           num_classes=1000,
           is_training=True,
           dropout_keep_prob=0.5,
           spatial_squeeze=True,
           scope='vgg_19',
           fc_conv_padding='VALID',
           global_pool=False):
  """Oxford Net VGG 19-Layers version E Example.
  Note: All the fully_connected layers have been transformed to conv2d layers.
        To use in classification mode, resize input to 224x224.
  Args:
    inputs: a tensor of size [batch_size, height, width, channels].
    num_classes: number of predicted classes. If 0 or None, the logits layer is
      omitted and the input features to the logits layer are returned instead.
    is_training: whether or not the model is being trained.
    dropout_keep_prob: the probability that activations are kept in the dropout
      layers during training.
    spatial_squeeze: whether or not should squeeze the spatial dimensions of the
      outputs. Useful to remove unnecessary dimensions for classification.
    scope: Optional scope for the variables.
    fc_conv_padding: the type of padding to use for the fully connected layer
      that is implemented as a convolutional layer. Use 'SAME' padding if you
      are applying the network in a fully convolutional manner and want to
      get a prediction map downsampled by a factor of 32 as an output.
      Otherwise, the output prediction map will be (input / 32) - 6 in case of
      'VALID' padding.
    global_pool: Optional boolean flag. If True, the input to the classification
      layer is avgpooled to size 1x1, for any input size. (This is not part
      of the original VGG architecture.)
  Returns:
    net: the output of the logits layer (if num_classes is a non-zero integer),
      or the non-dropped-out input to the logits layer (if num_classes is 0 or
      None).
    end_points: a dict of tensors with intermediate activations.
  """
  with tf.variable_scope(scope, 'vgg_19', [inputs]) as sc:
    end_points_collection = sc.original_name_scope + '_end_points'
    # Collect outputs for conv2d, fully_connected and max_pool2d.
    with slim.arg_scope([slim.conv2d, slim.fully_connected, slim.max_pool2d],
                        outputs_collections=end_points_collection):
      net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
      net = slim.max_pool2d(net, [2, 2], scope='pool1')
      net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
      net = slim.max_pool2d(net, [2, 2], scope='pool2')
      net = slim.repeat(net, 4, slim.conv2d, 256, [3, 3], scope='conv3')
      net = slim.max_pool2d(net, [2, 2], scope='pool3')
      net = slim.repeat(net, 4, slim.conv2d, 512, [3, 3], scope='conv4')
      net = slim.max_pool2d(net, [2, 2], scope='pool4')
      net = slim.repeat(net, 4, slim.conv2d, 512, [3, 3], scope='conv5')
      net = slim.max_pool2d(net, [2, 2], scope='pool5')

      # Use conv2d instead of fully_connected layers.
      net = slim.conv2d(net, 4096, [7, 7], padding=fc_conv_padding, scope='fc6')
      net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
                         scope='dropout6')
      net = slim.conv2d(net, 4096, [1, 1], scope='fc7')
      # Convert end_points_collection into a end_point dict.
      end_points = slim.utils.convert_collection_to_dict(end_points_collection)
      if global_pool:
        net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool')
        end_points['global_pool'] = net
      if num_classes:
        net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
                           scope='dropout7')
        net = slim.conv2d(net, num_classes, [1, 1],
                          activation_fn=None,
                          normalizer_fn=None,
                          scope='fc8')
        if spatial_squeeze:
          net = tf.squeeze(net, [1, 2], name='fc8/squeezed')
        end_points[sc.name + '/fc8'] = net
      return net, end_points
vgg_19.default_image_size = 224

# Alias
vgg_d = vgg_16
vgg_e = vgg_19