TensorFlow 2.0 搭建神经网络(扩展)

以下内容主要用于完善上节六步法搭建神经网络的功能，

• import
• train, test　　<数据增强>
• model = tf.keras.models.Sequential
• model.compile
• model.fit　　<断点续训>
• model.summary　　<参数提取，acc/loss 可视化>
• <前向推理实现应用>

1 数据增强 (增大数据量)

image_gen_train = tf.keras.preprocessing.image.ImageDataGenerator(
　　rescale = 所有数据将乘以该数值
　　rotation_range = 随机旋转角度数范围
　　width_shift_range = 随机宽度偏移量
　　height_shift_range = 随机高度偏移量
　　水平翻转：horizontal_flip = 是否随机水平翻转
　　随机缩放：zoom_range = 随机缩放的范围 [1-n，1+n] )
image_gen_train.fit(x_train)

　　mnist 数据集示例： 

import tensorflow as tf


mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)  # 给数据增加一个维度，使数据和网络结构匹配
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)

image_gen_train = tf.keras.preprocessing.image.ImageDataGenerator(
    rescale=1. / 1.,  # 如为图像，分母为255时，可归至0～1
    rotation_range=45,  # 随机45度旋转
    width_shift_range=.15,   # 宽度偏移
    height_shift_range=.15,  # 高度偏移
    horizontal_flip=True,   # 水平翻转
    zoom_range=0.5  # 将图像随机缩放阈量50％
)
image_gen_train.fit(x_train)

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(input_shape=(28, 28, 1)),
    tf.keras.layers.Dense(128, activation=tf.keras.activations.relu),
    tf.keras.layers.Dense(10, activation=tf.keras.activations.softmax)
])

model.compile(optimizer=tf.keras.optimizers.Adam(),
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=[tf.keras.metrics.sparse_categorical_accuracy])

model.fit(image_gen_train.flow(x_train, y_train, batch_size=32), epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()

2 断点续训，存取模型

 　　保存模型：借助 tensorflow 给出的回调函数，直接保存参数和网络。

tf.keras.callbacks.ModelCheckpoint(
　　filepath=路径文件名, 
　　save_weights_only=True, 
　　monitor='val_loss', # val_loss or loss 
　　save_best_only=True)
history = model.fit(x_train, y_train, batch_size=32, epochs=5, 
　　　　　　　　　　　　validation_data=(x_test, y_test), validation_freq=1, 
　　　　　　　　　　　　callbacks=[cp_callback])

　　注：monitor 配合 save_best_only 可以保存最优模型，包括训练损失最小模型、测试损失最小模型、训练准确率最高模型、测试准确率最高模型等。

　　读取模型：

checkpoint_save_path = './checkpoint/mnist.ckpt'
if os.path.exists(checkpoint_save_path + '.index'):
    print('----------load the model----------')
    model.load_weights(checkpoint_save_path)

　　示例：

import tensorflow as tf
import os


mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(input_shape=(28, 28)),
    tf.keras.layers.Dense(128, activation=tf.keras.activations.relu),
    tf.keras.layers.Dense(10, activation=tf.keras.activations.softmax)
])

model.compile(optimizer=tf.keras.optimizers.Adam(),
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=[tf.keras.metrics.sparse_categorical_accuracy])

checkpoint_save_path = './checkpoint/mnist.ckpt'
if os.path.exists(checkpoint_save_path + '.index'):
    print('----------load the model----------')
    model.load_weights(checkpoint_save_path)

cp_callback = tf.keras.callbacks.ModelCheckpoint(
    filepath=checkpoint_save_path,
    save_weights_only=True,
    monitor='val_loss',
    save_best_only=True
)

history = model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1,
                    callbacks=[cp_callback])
model.summary()

3 参数提取，写入文本

np.set_printoptions(threshold=np.inf)  # 超过多少省略显示，np.inf表示无限大
print(model.trainable_variables)  # 模型中可训练的参数
file = open('./weigths.txt', 'w')
for v in model.trainable_variables:
    file.write(str(v.name) + '\n')
    file.write(str(v.shape) + '\n')
    file.write(str(v.numpy()) + '\n')
file.close()

4 acc/loss 可视化

history = model.fit()

　　history：

　　训练集loss： loss

　　测试集loss： val_loss

　　训练集准确率： sparse_categorical_accuracy

　　测试集准确率： val_sparse_categorical_accuracy

acc = history.history['sparse_categorical_accuracy']
val_acc = history.history['val_sparse_categorical_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']

# show
plt.figure(figsize=(8, 8))
plt.subplot(1, 2, 1)
plt.plot(acc, label='Training Accuracy')
plt.plot(val_acc, label='Validation Accuracy')
plt.title('Training and Validation Accuracy')
plt.legend()

plt.subplot(1, 2, 2)
plt.plot(loss, label='Training loss')
plt.plot(val_loss, label='Validation loss')
plt.title('Training and Validation loss')
plt.legend()
plt.show()

5 实现给图识物的应用程序

 　　输入一张手写数字图片，输出识别值：

import tensorflow as tf
import os
import numpy as np
from PIL import Image
from matplotlib import pyplot as plt


model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation=tf.keras.activations.relu),
    tf.keras.layers.Dense(10, activation=tf.keras.activations.softmax)
])

checkpoint_save_path = './checkpoint/mnist.ckpt.index'
model.load_weights(checkpoint_save_path)

preNum = int(input('input the number of test pictures:'))
for i in range(preNum):
    image_path = input('the path of test picture:')
    img = Image.open(image_path)

    img = img.resize((28, 28), Image.ANTIALIAS)
    img_arr = np.array(img.convert('L'))

    for i in range(28):
        for j in range(28):
            if img_arr[i][j] < 200:
                img_arr[i][j] = 255
            else:
                img_arr[i][j] = 0
    img_arr = img_arr / 255.0

    x_predict = img_arr[tf.newaxis, ...]
    result = model.predict(x_predict)
    pred = tf.argmax(result, axis=1)
    print('\n')
    tf.print(pred)