4.2.5 Inception-mobile_net實戰

• Inception-Net

  Inception Net的思想是分組卷積，上一層分成幾組卷積，卷積完成之后在把分組的結果拼接起來

  可以進行擴展，每個組有很多層，這里只實現基本的分組卷積

  # 定義 Inception-Net的分組結構 def inception_block(x,output_channel_for_each_path,name):"""inception block implementation""""""Args:- x: 輸入數據- output_channel_for_each_path: 每組的輸出通道數目 eg: [10,20,30]- name: 每組的卷積命名"""# variable_scope 在這個scope下命名不會有沖突 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 會使得圖像變小，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]])# 在第四個維度（通道數）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])# 將向量變成具有三通道的圖片的格式 x_image = tf.reshape(x, [-1,3,32,32]) # 32*32 x_image = tf.transpose(x_image, perm = [0, 2, 3, 1])# 先經過一個普通的卷積層和池化層 # conv1：神經元圖,feature map,輸出圖像 conv1 = tf.layers.conv2d(x_image,32, # output channel number(3,3), # kernal sizepadding = 'same', # same 代表輸出圖像的大小沒有變化，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為了給這一層做一個命名，這樣會讓圖打印出來的時候會是一個有意義的圖)# 經過兩個個分組卷積 inception_2a = inception_block(pooling1, [16, 16, 16],name = 'inception_2a')inception_2b = inception_block(inception_2a, [16, 16, 16],name = 'inception_2b')# 接一個池化 pooling2 = tf.layers.max_pooling2d(inception_2b,(2, 2), (2, 2), name = 'pool2' )# 再經過兩個分組卷積核一個池化 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] 將三通道的圖形轉換成矩陣 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) 復制代碼

• Mobile-Net

  Mobile Net 的基本結構 深度可分類的卷積 -> BN ->RELU-> 1*1 的卷積 -> BN -> RELU

  這里BN先不加，這是下節課的內容

  def separable_conv_block(x,output_channel_number,name):"""separable_conv block implementation""""""Args:- x: 輸入數據- output_channel_number: 經過深度可分離卷積之后，再經過1*1 的卷積生成的通道數目- name: 每組的卷積命名"""# variable_scope 在這個scope下命名不會有沖突 conv1 = 'conv1' => scope_name/conv1with tf.variable_scope(name):input_channel = x.get_shape().as_list()[-1]# 將x 在 第四個維度（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])# 將向量變成具有三通道的圖片的格式 x_image = tf.reshape(x, [-1,3,32,32]) # 32*32 x_image = tf.transpose(x_image, perm = [0, 2, 3, 1])# conv1：神經元圖,feature map,輸出圖像 conv1 = tf.layers.conv2d(x_image,32, # output channel number(3,3), # kernal sizepadding = 'same', # same 代表輸出圖像的大小沒有變化，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為了給這一層做一個命名，這樣會讓圖打印出來的時候會是一個有意義的圖)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] 將三通道的圖形轉換成矩陣 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) 復制代碼

  這里的準確率是10000次百分之60，這是因為mobile net 的 參數減小和計算率減小影響了準確率。

• 這里的訓練我們都使用的是一萬次訓練，真正的神經網絡訓練遠不止于此，可能會達到100萬次的規模

總結

以上是生活随笔為你收集整理的3.5 卷积神经网络进阶-Inception-mobile_net 实战的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。