文章目錄

• 目錄
• • 1.Inception介紹
  • • 1.1 Inception結構
    • 1.2 Inception V1(GoogleNet)
    • 1.3 Inception V2(Batch Norm)
    • 1.4 Inception V3（Factorization）
    • 1.5 Inception V4（ResNet）
    • 1.5 Inception v1~v4 總結
    • 1.6 Inception進階
  • 2.Inception實現

目錄

1.Inception介紹

1.1 Inception結構

1.2 Inception V1(GoogleNet)

Naive Inception


Inception Module

GoogLeNet

1.3 Inception V2(Batch Norm)

1.4 Inception V3（Factorization）

1.5 Inception V4（ResNet）

Inception V4 相比 V3 主要是結合了微軟的 ResNet，將錯誤率進一步減少到 3.08%。

1.5 Inception v1~v4 總結

1.6 Inception進階

Inception v4 、Inception ResNet v1、Inception ResNet v2

Inception V4 網絡模型 Vs Inception ResNet 模型：

2.Inception實現

inceptionV2

def Conv2d_BN(x, filters, kernel_size, padding='same', strides=(1,1), name=None):if name is not None:bn_name = name + '_bn'conv_name = name + '_conv'else:bn_name = Noneconv_name = Nonex = Conv2D(filters=filters, kernel_size=kernel_size, padding=padding, strides=strides, activation='relu', name=conv_name)(x)x = BatchNormalization(axis=3, name=bn_name)(x)return xdef Inception(x, filters):branch_1x1 = Conv2d_BN(x, filters=filters, kernel_size=(1,1), padding='same', strides=(1,1), name=None)branch_3x3 = Conv2d_BN(x, filters=filters, kernel_size=(1,1), padding='same', strides=(1,1), name=None)branch_3x3 = Conv2d_BN(branch_3x3, filters=filters, kernel_size=(3,3), padding='same', strides=(1,1), name=None)branch_5x5 = Conv2d_BN(x, filters=filters, kernel_size=(1,1), padding='same', strides=(1,1), name=None)branch_5x5 = Conv2d_BN(branch_5x5, filters=filters, kernel_size=(5,5), padding='same', strides=(1,1), name=None)branch_pool = MaxPooling2D(pool_size=(3,3), strides=(1,1), padding='same')(x)branch_pool = Conv2d_BN(branch_pool, filters=filters, kernel_size=(1,1), padding='same', strides=(1,1), name=None)x = concatenate([branch_1x1, branch_3x3, branch_5x5, branch_pool], axis=3)return xdef Inception_v2(input_shape=(64,64,3), classes=6):x_input = Input(input_shape)"stage 1: "x = Conv2d_BN(x_input, filters=4, kernel_size=(5,5), strides=(1,1), padding='same')x = MaxPooling2D(pool_size=(3,3), strides=(2,2), padding='same')(x)x = Conv2d_BN(x, filters=8, kernel_size=(1,1), strides=(1,1), padding='same')x = Conv2d_BN(x, filters=8, kernel_size=(3,3), strides=(1,1), padding='same')x = MaxPooling2D(pool_size=(3,3), strides=(2,2), padding='same')(x)"stage 2: Inception_v2_block (*2)"x = Inception(x, 16) #4*16=64x = Inception(x, 16)x = MaxPooling2D(pool_size=(3,3), strides=(2,2), padding='same')(x)"stage 3: Inception_v2_block (*5)"x = Inception(x, 32)x = Inception(x, 32)x = Inception(x, 32) x = Inception(x, 64)x = Inception(x, 64)x = MaxPooling2D(pool_size=(3,3), strides=(2,2), padding='same')(x) "stage 4: Inception_v2_block (*2)"x = Inception(x, 128) x = Inception(x, 128)x = AveragePooling2D(pool_size=(4,4), strides=(1,1), padding='same')(x)x = Flatten()(x)"stage 5: fc"x = Dropout(0.5)(x) x = Dense(6,activation='softmax')(x) model = Model(inputs=x_input, outputs=x, name='Inception_v2')return model

總結

以上是生活随笔為你收集整理的深度学习（07）-- 经典CNN网络结构（Inception (v1-v4)）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。