• 論文：https://arxiv.org/pdf/1409.4842.pdf

inception v1

流程

- 整體框架 - 論文的目的 - 論文中的創新點 - keras代碼實現

整體框架

• inception模塊的設計
  該論文加入inception模塊，（b）相比于（a）來說，在3x3h和5x5的卷積前加入了1x1的卷積用來降維，也就是減少channel數，這樣大大減少計算量。為什么要這樣設計呢？因為inception v1之前的網絡都是一條路走到黑，通過加深網絡來提高準確率，但這樣大大增加了計算量。而inception模塊增加了網絡的深度和寬度，利用小卷積，既增加網絡結構的深度，又減少了計算量，還提高了網絡的準確率。
• 網絡結構表
  從表中來看，除了inception模塊，其他還是常規操作

論文的目的

• 減少計算參數量，減少訓練時間
• 提高網絡內部的資源利用率
• 既增加網絡的深度又增加網絡的寬度，還提升了準確率

論文中的創新點

• 1x1小卷積的提出，用于降維，減少了計算參數
• 最后使用了averagepool來適應網絡的如何輸入尺寸
• 加入了中間層輸出分支，在較低層進行分類并進行梯度的反向傳播

keras代碼實現

import keras from keras.layers import Input,Dense,Conv2D,MaxPool2D,BatchNormalization from keras.layers import concatenate,AvgPool2D,Dropout,Flatten from keras.models import Model from keras.utils import plot_model# inception模塊 def Inception(inputs=None,filter1=None,kernel1=1,filter3=None,kernel3=3,filter5=None,kernel5=5):# 1x1降維_1x1 = Conv2D(filters=filter1[0],kernel_size=kernel1,padding="same",activation="relu")(inputs)# 1x1降維reduce_1x1_3 = Conv2D(filters=filter1[1],kernel_size=kernel1,padding="same",activation="relu")(inputs)_3x3 = Conv2D(filters=filter3,kernel_size=kernel3,padding="same",activation="relu")(reduce_1x1_3)# 1x1降維reduce_1x1_5 = Conv2D(filters=filter1[2],kernel_size=kernel1,padding="same",activation="relu")(inputs)_5x5 = Conv2D(filters=filter5,kernel_size=kernel5,padding="same",activation="relu")(reduce_1x1_5)maxpool = MaxPool2D(pool_size=3,strides=1,padding="same")(inputs)# 1x1降維_1x1_max = Conv2D(filters=filter1[3],kernel_size=kernel1,padding="same",activation="relu")(maxpool)# 在通道上合并out = concatenate([_1x1,_3x3,_5x5,_1x1_max])return out# 分支輸出模塊 def output(net=None):net = AvgPool2D(pool_size=5,strides=3,padding="valid")(net)net = Conv2D(filters=128,kernel_size=1,strides=1,padding="valid",activation="relu")(net)net = Dense(units=1024,activation="relu")(net)net = Dropout(rate=0.7)(net)out = Dense(units=1000,activation="softmax")(net)return out# 網絡結構 --> 對著表看，很清晰 def Inception_v1():inputs = Input(shape=(224, 224, 3))net = Conv2D(filters=64, kernel_size=7,strides=2,padding="same",activation="relu")(inputs)net = BatchNormalization()(net)net = MaxPool2D(pool_size=3, strides=2, padding="same")(net)net = Conv2D(filters=64, kernel_size=1,strides=1,padding="same",activation="relu")(net)net = Conv2D(filters=192, kernel_size=3, strides=1,padding="same", activation="relu")(net)net = BatchNormalization()(net)net = MaxPool2D(pool_size=3, strides=2, padding="same")(net)net = Inception(inputs=net,filter1=[64,96,16,32],filter3=128,filter5=32)net = Inception(inputs=net,filter1=[128,128,32,64],filter3=192,filter5=96)net = MaxPool2D(pool_size=3, strides=2, padding="same")(net)net = Inception(inputs=net,filter1=[192,96,16,64],filter3=208,filter5=48)out1 = output(net)net = Inception(inputs=net,filter1=[160,112,24,64],filter3=224,filter5=64)net = Inception(inputs=net,filter1=[128,128,24,64],filter3=256,filter5=64)net = Inception(inputs=net,filter1=[112,144,32,64],filter3=288,filter5=64)out2 = output(net)net = Inception(inputs=net,filter1=[256,160,32,128],filter3=320,filter5=128)net = MaxPool2D(pool_size=3, strides=2,padding="same")(net)net = Inception(inputs=net,filter1=[256,160,32,128],filter3=320,filter5=32)net = Inception(inputs=net,filter1=[384,192,48,128],filter3=384,filter5=48)net = AvgPool2D(pool_size=7, strides=1,padding="valid")(net)net = Flatten()(net)net = Dropout(rate=0.4)(net)out3 = Dense(units=1000, activation="softmax")(net)model = Model(inputs=[inputs], outputs=[out1, out2, out3])return model# 畫出結構圖并保存 model = Inception_v1() plot_model(model, to_file='model.png',show_shapes=True,dpi=150)

• 網絡結構圖
  
• 每天進步一點點

總結

以上是生活随笔為你收集整理的论文简读（二）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。