Keras(三)实现深度神经网络

本文将在上节基础上，添加DNN深度学习模型。

一，打印使用的python库的版本信息

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

# 1,打印使用的python库的版本信息
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

#---output-----------
sys.version_info(major=3, minor=8, micro=5, releaselevel='final', serial=0)
matplotlib 3.3.2
numpy 1.19.1
pandas 1.0.3
sklearn 0.23.2
tensorflow 2.2.0
tensorflow.keras 2.3.0-tf

二，从keras.datasets中提取图片数据集-“训练数据”、“验证数据”、“测试数据”，并打印其维度

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)

#---------output--------------------
(5000, 28, 28) (5000,)
(55000, 28, 28) (55000,)
(10000, 28, 28) (10000,)

三，对数据标准化处理

# x = (x - u) / std
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
# x_train: [None, 28, 28] -> [None, 784]
x_train_scaled = scaler.fit_transform(
    x_train.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28)
x_valid_scaled = scaler.transform(
    x_valid.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28)
x_test_scaled = scaler.transform(
    x_test.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28)

四，构建DNN深度神经网络模型

# tf.keras.models.Sequential()
model = keras.models.Sequential()
model.add(keras.layers.Flatten(input_shape=[28, 28]))
for _ in range(50):
    model.add(keras.layers.Dense(100, activation="relu"))
model.add(keras.layers.Dense(10, activation="softmax"))

model.compile(loss="sparse_categorical_crossentropy",
              optimizer = keras.optimizers.SGD(0.01),
              metrics = ["accuracy"])

五，查看模型整体结构-及参数

print(model.summary())

六，添加回调函数、训练模型

# Tensorboard, earlystopping, ModelCheckpoint
logdir = './dnn-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=10, min_delta=1e-3),
]
history = model.fit(x_train_scaled, y_train, epochs=20,
                    validation_data=(x_valid_scaled, y_valid),
                    callbacks = callbacks)

七，绘制训练模型中，变化过程

在训练过程中，可能会发生梯度爆炸或梯度消失的情况。具体原因可参考：详解机器学习中的梯度消失、爆炸原因及其解决方法
此处附带笔者对sigmoid函数详细的求导、求极值过程链接如下：
sigmoid函数求导、求极值（史上最详细）

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)

八，调用估计器

print(model.evaluate(x_test_scaled, y_test, verbose=0))

九，代码总结

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

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

# 1,打印使用的python库的版本信息
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)


# 2,从keras.datasets中提取图片数据集-“训练数据”、“验证数据”、“测试数据”，并打印其维度
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)

# 3,对数据标准化处理
# x = (x - u) / std
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
# x_train: [None, 28, 28] -> [None, 784]
x_train_scaled = scaler.fit_transform(
    x_train.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28)
x_valid_scaled = scaler.transform(
    x_valid.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28)
x_test_scaled = scaler.transform(
    x_test.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28)

# 4,构建DNN深度神经网络模型
# tf.keras.models.Sequential()
model = keras.models.Sequential()
model.add(keras.layers.Flatten(input_shape=[28, 28]))
for _ in range(30):
    model.add(keras.layers.Dense(100, activation="relu"))
model.add(keras.layers.Dense(10, activation="softmax"))

model.compile(loss="sparse_categorical_crossentropy",
              optimizer = keras.optimizers.SGD(0.01),
              metrics = ["accuracy"])

# 5,查看模型整体结构-及参数
print(model.summary())

# 6,添加回调函数、训练模型
# Tensorboard, earlystopping, ModelCheckpoint
logdir = './dnn-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=10, min_delta=1e-3),
]
history = model.fit(x_train_scaled, y_train, epochs=20,
                    validation_data=(x_valid_scaled, y_valid),
                    callbacks = callbacks)

# 7,绘制训练模型中，变化过程
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)

# 1. 参数众多，训练不充分
# 2. 梯度消失 -> 链式法则 -> 复合函数f(g(x))

# 8,调用估计器
print(model.evaluate(x_test_scaled, y_test, verbose=0))