4.2.5 Inception-mobile_net实战

• Inception-Net

  Inception Net的思想是分组卷积，上一层分成几组卷积，卷积完成之后在把分组的结果拼接起来

  可以进行扩展，每个组有很多层，这里只实现基本的分组卷积

  # 定义 Inception-Net的分组结构
  def inception_block(x,output_channel_for_each_path,name):"""inception block implementation""""""Args:- x: 输入数据- output_channel_for_each_path: 每组的输出通道数目 eg: [10,20,30]- name: 每组的卷积命名"""# variable_scope 在这个scope下命名不会有冲突 conv1 = 'conv1' => scope_name/conv1with tf.variable_scope(name):conv1_1 = tf.layers.conv2d(x,output_channel_for_each_path[0],(1, 1),strides = (1,1),padding = 'same',activation = tf.nn.relu,name = 'conv1_1')conv3_3 = tf.layers.conv2d(x,output_channel_for_each_path[1],(3, 3),strides = (1,1),padding = 'same',activation = tf.nn.relu,name = 'conv3_3')conv5_5 = tf.layers.conv2d(x,output_channel_for_each_path[0],(5, 5),strides = (1,1),padding = 'same',activation = tf.nn.relu,name = 'conv5_5')max_pooling = tf.layers.max_pooling2d(x,(2,2),(2,2),name = 'max_pooling')# max_pooling 会使得图像变小，所以需要paddingmax_pooling_shape = max_pooling.get_shape().as_list()[1:]input_shape = x.get_shape().as_list()[1:]width_padding = (input_shape[0] - max_pooling_shape[0]) // 2height_padding = (input_shape[1] - max_pooling_shape[1]) // 2padded_pooling = tf.pad(max_pooling,[[0,0],[width_padding,width_padding],[height_padding,height_padding],[0,0]])# 在第四个维度（通道数）上做拼接concat_layer = tf.concat([conv1_1, conv3_3, conv5_5, padded_pooling],axis = 3)return concat_layerx = tf.placeholder(tf.float32, [None, 3072])
  y = tf.placeholder(tf.int64, [None])# 将向量变成具有三通道的图片的格式
  x_image = tf.reshape(x, [-1,3,32,32])
  # 32*32
  x_image = tf.transpose(x_image, perm = [0, 2, 3, 1])# 先经过一个普通的卷积层和池化层
  # conv1：神经元图,feature map,输出图像
  conv1 = tf.layers.conv2d(x_image,32, # output channel number(3,3), # kernal sizepadding = 'same', # same 代表输出图像的大小没有变化，valid 代表不做paddingactivation = tf.nn.relu,name = 'conv1')
  # 16*16
  pooling1 = tf.layers.max_pooling2d(conv1,(2, 2), # kernal size(2, 2), # stridename = 'pool1' # name为了给这一层做一个命名，这样会让图打印出来的时候会是一个有意义的图)# 经过两个个分组卷积
  inception_2a = inception_block(pooling1, [16, 16, 16],name = 'inception_2a')inception_2b = inception_block(inception_2a, [16, 16, 16],name = 'inception_2b')# 接一个池化
  pooling2 = tf.layers.max_pooling2d(inception_2b,(2, 2), (2, 2), name = 'pool2' )# 再经过两个分组卷积核一个池化
  inception_3a = inception_block(pooling2, [16, 16, 16],name = 'inception_3a')inception_3b = inception_block(inception_3a, [16, 16, 16],name = 'inception_3b')pooling3 = tf.layers.max_pooling2d(inception_3b,(2, 2), (2, 2), name = 'pool3' )# [None, 4*4*42] 将三通道的图形转换成矩阵
  flatten = tf.layers.flatten(pooling3)
  y_ = tf.layers.dense(flatten, 10)# 交叉熵
  loss = tf.losses.sparse_softmax_cross_entropy(labels=y, logits=y_)
  # y_-> softmax
  # y -> one_hot
  # loss = ylogy_# bool
  predict = tf.argmax(y_, 1)
  # [1,0,1,1,1,0,0,0]
  correct_prediction = tf.equal(predict, y)
  accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float64))with tf.name_scope('train_op'):train_op = tf.train.AdamOptimizer(1e-3).minimize(loss)
  复制代码

• Mobile-Net

  Mobile Net 的基本结构 深度可分类的卷积 -> BN ->RELU-> 1*1 的卷积 -> BN -> RELU

  这里BN先不加，这是下节课的内容

  def separable_conv_block(x,output_channel_number,name):"""separable_conv block implementation""""""Args:- x: 输入数据- output_channel_number: 经过深度可分离卷积之后，再经过1*1 的卷积生成的通道数目- name: 每组的卷积命名"""# variable_scope 在这个scope下命名不会有冲突 conv1 = 'conv1' => scope_name/conv1with tf.variable_scope(name):input_channel = x.get_shape().as_list()[-1]# 将x 在 第四个维度（axis+1） 上 拆分成 input_channel 份# channel_wise_x: [channel1, channel2, ...]channel_wise_x = tf.split(x, input_channel, axis = 3)output_channels = []for i in range(len(channel_wise_x)):output_channel = tf.layers.conv2d(channel_wise_x[i],1,(3,3),strides = (1,1),padding = 'same',activation = tf.nn.relu,name = 'conv_%d' % i)output_channels.append(output_channel)concat_layers = tf.concat(output_channels, axis = 3)conv1_1 = tf.layers.conv2d(concat_layers,output_channel_number,(1,1),strides = (1,1),padding = 'same',activation = tf.nn.relu,name = 'conv1_1')return conv1_1x = tf.placeholder(tf.float32, [None, 3072])
  y = tf.placeholder(tf.int64, [None])# 将向量变成具有三通道的图片的格式
  x_image = tf.reshape(x, [-1,3,32,32])
  # 32*32
  x_image = tf.transpose(x_image, perm = [0, 2, 3, 1])# conv1：神经元图,feature map,输出图像
  conv1 = tf.layers.conv2d(x_image,32, # output channel number(3,3), # kernal sizepadding = 'same', # same 代表输出图像的大小没有变化，valid 代表不做paddingactivation = tf.nn.relu,name = 'conv1')
  # 16*16
  pooling1 = tf.layers.max_pooling2d(conv1,(2, 2), # kernal size(2, 2), # stridename = 'pool1' # name为了给这一层做一个命名，这样会让图打印出来的时候会是一个有意义的图)separable_2a = separable_conv_block(pooling1, 32,name = 'separable_2a')separable_2b = separable_conv_block(separable_2a, 32,name = 'separable_2b')pooling2 = tf.layers.max_pooling2d(separable_2b,(2, 2), (2, 2), name = 'pool2' )separable_3a = separable_conv_block(pooling2, 32,name = 'separable_3a')separable_3b = separable_conv_block(separable_3a, 32,name = 'separable_3b')pooling3 = tf.layers.max_pooling2d(separable_3b,(2, 2), (2, 2), name = 'pool3')# [None, 4*4*42] 将三通道的图形转换成矩阵
  flatten = tf.layers.flatten(pooling3)
  y_ = tf.layers.dense(flatten, 10)# 交叉熵
  loss = tf.losses.sparse_softmax_cross_entropy(labels=y, logits=y_)
  # y_-> softmax
  # y -> one_hot
  # loss = ylogy_# bool
  predict = tf.argmax(y_, 1)
  # [1,0,1,1,1,0,0,0]
  correct_prediction = tf.equal(predict, y)
  accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float64))with tf.name_scope('train_op'):train_op = tf.train.AdamOptimizer(1e-3).minimize(loss)
  复制代码

  这里的准确率是10000次百分之60，这是因为mobile net 的 参数减小和计算率减小影响了准确率。

• 这里的训练我们都使用的是一万次训练，真正的神经网络训练远不止于此，可能会达到100万次的规模