深度学习： VGG 网络-CSDN博客

本文链接：https://blog.csdn.net/wss794/article/details/103907972

1 VGG 网络网络结构

VGG16包含了16个隐藏层：13个卷积层和3个全连接层

VGG19包含了19个隐藏层：16个卷积层和3个全连接层

2 代码

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

import tensorflow as tf
slim = tf.contrib.slim


def vgg_arg_scope(weight_decay=0.0005):
    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


def vgg_16(inputs,
           num_classes,
           is_training,
           dropout_keep_prob=0.5,
           spatial_squeeze=True,
           scope='vgg_16',
           fc_conv_padding='VALID',
           global_pool=False):
    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, [3, 3], padding=fc_conv_padding, scope='fc7')
            # print(net)
            # 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')
                # print(net)
            if spatial_squeeze:
                net = tf.squeeze(net, [1, 2], name='fc8/squeezed')
            end_points[sc.name + '/fc8'] = net
            return net, end_points


def vgg_19(inputs,
           num_classes,
           is_training,
           dropout_keep_prob=0.5,
           spatial_squeeze=True,
           scope='vgg_19',
           fc_conv_padding='VALID',
           global_pool=False):

    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, [3, 3], padding=fc_conv_padding, scope='fc7')
            # print(net)
            # 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')
                # print(net)
            if spatial_squeeze:
                net = tf.squeeze(net, [1, 2], name='fc8/squeezed')
            end_points[sc.name + '/fc8'] = net
            return net, end_points


if __name__ == '__main__':
    with slim.arg_scope(vgg_arg_scope()):
        inputs = tf.placeholder(tf.float32, [None, 304, 304, 3], name='input')
        outputs, end_points = vgg_19(inputs, num_classes=2, is_training=True)
        pass

可参考的资料：

https://blog.csdn.net/qq_29893385/article/details/81207082

https://blog.csdn.net/qq_41760767/article/details/97776671#11VGG_2