Python高级架构模式的整理

from keras import layers

x = ...

y = layers.Conv2D(128, 3, activation='relu', padding='same')(x)

y = layers.Conv2D(128, 3, activation='relu', padding='same')(y)

y = layers.MaxPooling2D(2, strides=2)(y)

# 形状不同，要做线性变换：

residual = layers.Conv2D(128, 1, strides=2, padding='same')(x)  # 使用 1×1 卷积，将 x 线性下采样为与 y 具有相同的形状

y = layers.add([y, residual])

# Conv

conv_model.add(layers.Conv2D(32, 3, activation='relu'))

conv_model.add(layers.BatchNormalization())

# Dense

dense_model.add(layers.Dense(32, activation='relu'))

dense_model.add(layers.BatchNormalization())

3、深度可分离卷积层，在Keras中被称为SeparableConv2D，其功能与普通Conv2D相同。

但是SeparableConv2D比Conv2D轻，训练快，精度高。

from tensorflow.keras.models import Sequential, Model

from tensorflow.keras import layers

height = 64

width = 64

channels = 3

num_classes = 10

model = Sequential()

model.add(layers.SeparableConv2D(32, 3,

                                 activation='relu',

                                 input_shape=(height, width, channels,)))

model.add(layers.SeparableConv2D(64, 3, activation='relu'))

model.add(layers.MaxPooling2D(2))

model.add(layers.SeparableConv2D(64, 3, activation='relu'))

model.add(layers.SeparableConv2D(128, 3, activation='relu'))

model.add(layers.MaxPooling2D(2))

model.add(layers.SeparableConv2D(64, 3, activation='relu'))

model.add(layers.SeparableConv2D(128, 3, activation='relu'))

model.add(layers.GlobalAveragePooling2D())

model.add(layers.Dense(32, activation='relu'))

model.add(layers.Dense(num_classes, activation='softmax'))

model.compile(optimizer='rmsprop', loss='categorical_crossentropy')