python神经网络Xception模型复现详解 python神经网络Xception模型复现详

什么是Xception模型
Xception网络部分实现代码
图片预测

Xception是继Inception后提出的对Inception v3的另一种改进，学一学总是好的

什么是Xception模型 【python神经网络Xception模型复现详解】Xception是谷歌公司继Inception后，提出的InceptionV3的一种改进模型，其改进的主要内容为采用depthwise separable convolution来替换原来Inception v3中的多尺寸卷积核特征响应操作。
在讲Xception模型之前，首先要讲一下什么是depthwise separable convolution（深度可分离卷积块）。
深度可分离卷积块由两个部分组成，分别是深度可分离卷积和1x1普通卷积，深度可分离卷积的卷积核大小一般是3x3的，便于理解的话我们可以把它当作是特征提取，1x1的普通卷积可以完成通道数的调整。
下图为深度可分离卷积块的结构示意图：

文章图片

深度可分离卷积块的目的是使用更少的参数来代替普通的3x3卷积。
我们可以进行一下普通卷积和深度可分离卷积块的对比：
假设有一个3×3大小的卷积层，其输入通道为16、输出通道为32。具体为，32个3×3大小的卷积核会遍历16个通道中的每个数据，最后可得到所需的32个输出通道，所需参数为16×32×3×3=4608个。
应用深度可分离卷积，用16个3×3大小的卷积核分别遍历16通道的数据，得到了16个特征图谱。在融合操作之前，接着用32个1×1大小的卷积核遍历这16个特征图谱，所需参数为16×3×3+16×32×1×1=656个。
可以看出来depthwise separable convolution可以减少模型的参数。
通俗地理解深度可分离卷积结构块，就是3x3的卷积核厚度只有一层，然后在输入张量上一层一层地滑动，每一次卷积完生成一个输出通道，当卷积完成后，再利用1x1的卷积调整厚度。
（视频中有些许错误，感谢zl960929的提醒，Xception使用的深度可分离卷积块SeparableConv2D也就是先深度可分离卷积再进行1x1卷积。）
对于Xception模型而言，其一共可以分为3个flow，分别是Entry flow、Middle flow、Exit flow；分为14个block，其中Entry flow中有4个、Middle flow中有8个、Exit flow中有2个。具体结构如下：

文章图片

其内部主要结构就是残差卷积网络搭配SeparableConv2D层实现一个个block，在Xception模型中，常见的两个block的结构如下。
这个主要在Entry flow和Exit flow中：

文章图片

这个主要在Middle flow中：

文章图片

Xception网络部分实现代码

#-------------------------------------------------------------##Xception的网络部分#-------------------------------------------------------------#from keras.preprocessing import imagefrom keras.models import Modelfrom keras import layersfrom keras.layers import Dense,Input,BatchNormalization,Activation,Conv2D,SeparableConv2D,MaxPooling2Dfrom keras.layers import GlobalAveragePooling2D,GlobalMaxPooling2Dfrom keras import backend as Kfrom keras.applications.imagenet_utils import decode_predictionsdef Xception(input_shape = [299,299,3],classes=1000):img_input = Input(shape=input_shape)#--------------------------## Entry flow#--------------------------##--------------------## block1#--------------------## 299,299,3 -> 149,149,64x = Conv2D(32, (3, 3), strides=(2, 2), use_bias=False, name='block1_conv1')(img_input)x = BatchNormalization(name='block1_conv1_bn')(x)x = Activation('relu', name='block1_conv1_act')(x)x = Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x)x = BatchNormalization(name='block1_conv2_bn')(x)x = Activation('relu', name='block1_conv2_act')(x)#--------------------## block2#--------------------## 149,149,64 -> 75,75,128residual = Conv2D(128, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x)residual = BatchNormalization()(residual)x = SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv1')(x)x = BatchNormalization(name='block2_sepconv1_bn')(x)x = Activation('relu', name='block2_sepconv2_act')(x)x = SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv2')(x)x = BatchNormalization(name='block2_sepconv2_bn')(x)x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block2_pool')(x)x = layers.add([x, residual])#--------------------## block3#--------------------## 75,75,128 -> 38,38,256residual = Conv2D(256, (1, 1), strides=(2, 2),padding='same', use_bias=False)(x)residual = BatchNormalization()(residual)x = Activation('relu', name='block3_sepconv1_act')(x)x = SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv1')(x)x = BatchNormalization(name='block3_sepconv1_bn')(x)x = Activation('relu', name='block3_sepconv2_act')(x)x = SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv2')(x)x = BatchNormalization(name='block3_sepconv2_bn')(x)x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block3_pool')(x)x = layers.add([x, residual])#--------------------## block4#--------------------## 38,38,256 -> 19,19,728residual = Conv2D(728, (1, 1), strides=(2, 2),padding='same', use_bias=False)(x)residual = BatchNormalization()(residual)x = Activation('relu', name='block4_sepconv1_act')(x)x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv1')(x)x = BatchNormalization(name='block4_sepconv1_bn')(x)x = Activation('relu', name='block4_sepconv2_act')(x)x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv2')(x)x = BatchNormalization(name='block4_sepconv2_bn')(x)x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block4_pool')(x)x = layers.add([x, residual])#--------------------------## Middle flow#--------------------------##--------------------## block5--block12#--------------------## 19,19,728 -> 19,19,728for i in range(8):residual = xprefix = 'block' + str(i + 5)x = Activation('relu', name=prefix + '_sepconv1_act')(x)x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv1')(x)x = BatchNormalization(name=prefix + '_sepconv1_bn')(x)x = Activation('relu', name=prefix + '_sepconv2_act')(x)x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv2')(x)x = BatchNormalization(name=prefix + '_sepconv2_bn')(x)x = Activation('relu', name=prefix + '_sepconv3_act')(x)x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv3')(x)x = BatchNormalization(name=prefix + '_sepconv3_bn')(x)x = layers.add([x, residual])#--------------------------## Exit flow#--------------------------##--------------------## block13#--------------------## 19,19,728 -> 10,10,1024residual = Conv2D(1024, (1, 1), strides=(2, 2),padding='same', use_bias=False)(x)residual = BatchNormalization()(residual)x = Activation('relu', name='block13_sepconv1_act')(x)x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block13_sepconv1')(x)x = BatchNormalization(name='block13_sepconv1_bn')(x)x = Activation('relu', name='block13_sepconv2_act')(x)x = SeparableConv2D(1024, (3, 3), padding='same', use_bias=False, name='block13_sepconv2')(x)x = BatchNormalization(name='block13_sepconv2_bn')(x)x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block13_pool')(x)x = layers.add([x, residual])#--------------------## block14#--------------------## 10,10,1024 -> 10,10,2048x = SeparableConv2D(1536, (3, 3), padding='same', use_bias=False, name='block14_sepconv1')(x)x = BatchNormalization(name='block14_sepconv1_bn')(x)x = Activation('relu', name='block14_sepconv1_act')(x)x = SeparableConv2D(2048, (3, 3), padding='same', use_bias=False, name='block14_sepconv2')(x)x = BatchNormalization(name='block14_sepconv2_bn')(x)x = Activation('relu', name='block14_sepconv2_act')(x)x = GlobalAveragePooling2D(name='avg_pool')(x)x = Dense(classes, activation='softmax', name='predictions')(x)inputs = img_inputmodel = Model(inputs, x, name='xception')model.load_weights("xception_weights_tf_dim_ordering_tf_kernels.h5")return model

图片预测建立网络后，可以用以下的代码进行预测。

def preprocess_input(x):x /= 255.x -= 0.5x *= 2.return xif __name__ == '__main__':model = Xception()img_path = 'elephant.jpg'img = image.load_img(img_path, target_size=(299, 299))x = image.img_to_array(img)x = np.expand_dims(x, axis=0)x = preprocess_input(x)print('Input image shape:', x.shape)preds = model.predict(x)print(np.argmax(preds))print('Predicted:', decode_predictions(preds))

预测所需的已经训练好的Xception模型可以在https://github.com/fchollet/deep-learning-models/releases下载。非常方便。
预测结果为：

Predicted: [[('n02504458', 'African_elephant', 0.47570863), ('n01871265', 'tusker', 0.3173351), ('n02504013', 'Indian_elephant', 0.030323735), ('n02963159', 'cardigan', 0.0007877756), ('n02410509', 'bison', 0.00075616257)]]

以上就是python神经网络Xception模型复现详解的详细内容，更多关于Xception模型的复现详解的资料请关注脚本之家其它相关文章！