tensorflow2.0学习笔记：深度可分离卷积

1. 深度可分离卷积本质上是一种分支网络结构，分支网络结构有以下好处：
   a.可提供不同的视野域
   b.提升效率
2. 深度可分离卷积使用通道分支，能够减少参数提高计算效率，但同时也会造成梯度损失。深度可分离卷积由于其训练参数小的特点可以在手机上实现。
3. tf.keras 实现较简单，仅需把卷积神经网络中的除输入层外的Conv2D替换为SeparableConv2D。（tensorflow2.0学习笔记：卷积神经网络(CNN)）

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__)

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)

#归一化：x = (x-mu)/std 均值为0，方差为1
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)

print(np.max(x_train_scaled),np.min(x_train_scaled))

# 深度可分离卷积层 SeparableConv2D
model = keras.models.Sequential()
# 输入层依然使用Conv2D，后续使用SeparableConv2D
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 = "adam",
             metrics = ["accuracy"])
model.summary()

#callbacks: Tensorboard , earlystopping , ModelCheckpoint
#设置一个文件夹
logdir = os.path.join('./separable_cnn_callbacks')
if not os.path.exists(logdir):
    os.mkdir(logdir)
output_model_file = os.path.join(logdir,"fashion_mnist_model.h5")

callbacks = [
    keras.callbacks.ModelCheckpoint(output_model_file,save_best_only = True),
    keras.callbacks.EarlyStopping(monitor="val_loss",patience=5,min_delta=1e-3)
]

history = model.fit(x_train_scaled,y_train,epochs=1,
                    validation_data=(x_valid_scaled,y_valid))

def plot_learning_curve(history):
    pd.DataFrame(history.history).plot(figsize=(8,5))
    plt.grid(True)
    plt.gca().set_ylim(0,3)
    plt.show()
#DateFrame 数据类型的作图
plot_learning_curve(history)

y = model.evaluate(x_test_scaled,y_test)