深度可分离卷积网络的理论与实战（TF2.0）

1、深度可分离卷积网络的理论

深度可分离卷积是普通卷积操作的一个变种，它可以替代不同卷积，从而构成卷积神经网络。

以精度损失为代价去换取计算量的减少和参数量的减少，从而使得深度可分离卷积网络可以在手机端运行。

用右图的结构代替左图： 它的好处是，有不同尺寸的视野域，

如下图是Inception V3的结构：从左到右的视野域为：1*1,3*3,6*6,5*5，在这四个分支上有4种不同的视野域，4种不同的视野域也就提取出了4种不同尺寸的图像特征。最后输出的信息就更丰富，效果更好。并且相对于不做分支时会提高效率，减少计算量。

深度可分离卷积也是一种分支的网络结构，只不过它的分支建立在不同通道之上。

输入->1*1卷积 = 多通道输出->在这些通道上建立分支（3个通道，3个分支）->得到不同结果做合并

深度可分离卷积相比于普通卷积计算量少很多：DK代表卷积核大小，M代表输入通道数，N代表输出通道数，DF代表输入图像大小

2、深度可分离卷积网络的实战（TF2.0）

在keras里深度可分离卷积已经被实现了，因此可以像使用Conv2D一样来使用深度可分离卷积。在深度可分离卷积神经网络里面，通常在输入层上使用普通的卷积，在输入层之外的地方使用深度可分离卷积。网络结构如下所示：

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d (Conv2D)              (None, 28, 28, 32)        320       
_________________________________________________________________
separable_conv2d (SeparableC (None, 28, 28, 32)        1344      
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 14, 14, 32)        0         
_________________________________________________________________
separable_conv2d_1 (Separabl (None, 14, 14, 64)        2400      
_________________________________________________________________
separable_conv2d_2 (Separabl (None, 14, 14, 64)        4736      
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 7, 7, 64)          0         
_________________________________________________________________
separable_conv2d_3 (Separabl (None, 7, 7, 128)         8896      
_________________________________________________________________
separable_conv2d_4 (Separabl (None, 7, 7, 128)         17664     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 3, 3, 128)         0         
_________________________________________________________________
flatten (Flatten)            (None, 1152)              0         
_________________________________________________________________
dense (Dense)                (None, 128)               147584    
_________________________________________________________________
dense_1 (Dense)              (None, 10)                1290      
=================================================================
Total params: 184,234
Trainable params: 184,234
Non-trainable params: 0
_________________________________________________________________

附代码：

import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf

from tensorflow import keras

print(tf.__version__)
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

fashion_mnist = keras.datasets.fashion_mnist
(x_train_all, y_train_all), (x_test, y_test) = fashion_mnist.load_data()
x_valid, x_train = x_train_all[:5000], x_train_all[5000:]
y_valid, y_train = y_train_all[:5000], y_train_all[5000:]

print(x_valid.shape, y_valid.shape)
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(
    x_train.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)
x_valid_scaled = scaler.transform(
    x_valid.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)
x_test_scaled = scaler.transform(
    x_test.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)

model = keras.models.Sequential()
model.add(keras.layers.Conv2D(filters=32, kernel_size=3,
                              padding='same',
                              activation='selu',
                              input_shape=(28, 28, 1)))
model.add(keras.layers.SeparableConv2D(filters=32, kernel_size=3,
                                       padding='same',
                                       activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.SeparableConv2D(filters=64, kernel_size=3,
                                       padding='same',
                                       activation='selu'))
model.add(keras.layers.SeparableConv2D(filters=64, kernel_size=3,
                                       padding='same',
                                       activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.SeparableConv2D(filters=128, kernel_size=3,
                                       padding='same',
                                       activation='selu'))
model.add(keras.layers.SeparableConv2D(filters=128, kernel_size=3,
                                       padding='same',
                                       activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(128, activation='selu'))
model.add(keras.layers.Dense(10, activation="softmax"))

model.compile(loss="sparse_categorical_crossentropy",
              optimizer = "sgd",
              metrics = ["accuracy"])

model.summary()

logdir = os.path.join("separable-cnn-selu-callbacks")
if not os.path.exists(logdir):
    os.mkdir(logdir)
output_model_file = os.path.join(logdir,
                                 "fashion_mnist_model.h5")

callbacks = [
    keras.callbacks.TensorBoard(logdir),
    keras.callbacks.ModelCheckpoint(output_model_file,
                                    save_best_only = True),
    keras.callbacks.EarlyStopping(patience=5, min_delta=1e-3),
]
history = model.fit(x_train_scaled, y_train, epochs=10,
                    validation_data=(x_valid_scaled, y_valid),
                    callbacks = callbacks)

def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8, 5))
    plt.grid(True)
    plt.gca().set_ylim(0, 3)
    plt.show()

plot_learning_curves(history)
model.evaluate(x_test_scaled, y_test, verbose = 0)