神经网络八股扩展（tensorflow）_4

六步法的扩展：

Import
train，test（自制数据集，数据增强）
Sequential/Class
model.compile
model.fit（断点续训）
model.summary（参数提取，acc/loss可视化，前向推理应用）

自制数据集导入：

import tensorflow as tf
from PIL import Image
import numpy as np
import os

train_path = './mnist_image_label/mnist_train_jpg_60000/'
train_txt = './mnist_image_label/mnist_train_jpg_60000.txt'
x_train_savepath = './mnist_image_label/mnist_x_train.npy'
y_train_savepath = './mnist_image_label/mnist_y_train.npy'

test_path = './mnist_image_label/mnist_test_jpg_10000/'
test_txt = './mnist_image_label/mnist_test_jpg_10000.txt'
x_test_savepath = './mnist_image_label/mnist_x_test.npy'
y_test_savepath = './mnist_image_label/mnist_y_test.npy'


def generateds(path, txt):
    f = open(txt, 'r')  # 以只读形式打开txt文件
    contents = f.readlines()  # 读取文件中所有行
    f.close()  # 关闭txt文件
    x, y_ = [], []  # 建立空列表
    for content in contents:  # 逐行取出
        value = content.split()  # 以空格分开，图片路径为value[0] , 标签为value[1] , 存入列表
        img_path = path + value[0]  # 拼出图片路径和文件名
        img = Image.open(img_path)  # 读入图片
        img = np.array(img.convert('L'))  # 图片变为28位宽灰度值的np.array格式
        img = img / 255.  # 数据归一化 （实现预处理）
        x.append(img)  # 归一化后的数据，贴到列表x
        y_.append(value[1])  # 标签贴到列表y_
        print('loading : ' + content)  # 打印状态提示

    x = np.array(x)  # 变为np.array格式
    y_ = np.array(y_)  # 变为np.array格式
    y_ = y_.astype(np.int64)  # 变为64位整型
    return x, y_  # 返回输入特征x，返回标签y_


if os.path.exists(x_train_savepath) and os.path.exists(y_train_savepath) and os.path.exists(
        x_test_savepath) and os.path.exists(y_test_savepath):
    print('-------------Load Datasets-----------------')
    x_train_save = np.load(x_train_savepath)
    y_train = np.load(y_train_savepath)
    x_test_save = np.load(x_test_savepath)
    y_test = np.load(y_test_savepath)
    x_train = np.reshape(x_train_save, (len(x_train_save), 28, 28))
    x_test = np.reshape(x_test_save, (len(x_test_save), 28, 28))
else:
    print('-------------Generate Datasets-----------------')
    x_train, y_train = generateds(train_path, train_txt)
    x_test, y_test = generateds(test_path, test_txt)

    print('-------------Save Datasets-----------------')
    x_train_save = np.reshape(x_train, (len(x_train), -1))
    x_test_save = np.reshape(x_test, (len(x_test), -1))
    np.save(x_train_savepath, x_train_save)
    np.save(y_train_savepath, y_train)
    np.save(x_test_savepath, x_test_save)
    np.save(y_test_savepath, y_test)

数据增强：

扩展数据集，对图像的增强就是对图像的简单形变，用来应变因拍照角度不同引起的图片变形

from tensorflow.keras.preprocessing.image import ImageDataGenerator

image_gen_train = tf.kears.preprocessing.image.ImageDataGeneration(
    rescale = 输入量×的超参数  # 改变输入大小
    rotation_range = 图像随机旋转角度的范围
    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 = 是否随机水平旋转
    随机缩放：zoom_range = 随机缩放的范围[1-n,1+n])
image_gen_train.fit(x_train)
其中x_train是四维数据，所以对x_train进行reshape
x_train = x_train.reshape(x_train.shape[0],28,28,1)  # 把(60000,28,28)转换成(60000,28,28,1)，1是单通道，是灰度值
model.fit(x_train,y_train,bacth_size=32...)换为
model.fit(image_gen_train.flow(x_train,y_train,bacth_size=32),...)

数据增强在小数据量下可以增强模型泛化性

断点续训可以存取模型

读取模型：load_weights(路径文件名)

model_save_path = './checkpoint/mnist.ckpt'  # 存放的路径和文件名，命名为ckpt文件
if os.path.exists(model_save_path + '.index'):  # 生成ckpt文件的时候会同步生成index索引表，所以判断索引表是否存在就可以判断是否已保存过模型参数
    model.load_weights(model_save_path)  # 如果有模型参数，可以直接读取

保存模型参数：

tf.keras.callbacks.ModelCheckpoint(
    filepath=文件存储路径,
    save_weights_only=True/False,  # 是否只保留模型参数
    save_best_only=True/False,  # 是否只保留最优结果
)
history=model.fit(callbacks=[cp_callback])  # 训练的时候加入callbacks选项，记录到history中

如

cp_callback = tf.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
                                           save_weights_only=True,
                                           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])

参数提取

model.trainable_variables 返回模型可训练参数
np.set_printoptions(threshold=np.inf)
print(model.trainable_variables) 打印出可训练参数

import tensorflow as tf
import os
import numpy as np
np.set_printoptions(threshold=np.inf)  # 设置打印参数时是无省略号的
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(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

# 断点续训：18~26
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,
                                                 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()
print(model.trainable_variables)  # 打印可训练参数
# 把可训练参数存入txt文件中：30~35
file = open('./weights.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()

acc/loss可视化

history=model.fit(…)时history记录了
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
所以可用history.history[‘…’]提取出来

# 显示训练集和验证集的acc和loss曲线
acc = history.history['sparse_categorical_accuracy']
val_acc = history.history['val_sparse_categorical_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']

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()

训练模型之后的预测：

predict(输入特征，batch_size=整数）
给出输入特征，输出预测结果
实现预测的三步：
1.复现模型：model=tf.keras.models.Sequential([…])
2.加载参数：model.load_weights(model_save_path)
3.预测结果：result=model.predict(x_predict)

from PIL import Image
import numpy as np
import tensorflow as tf

model_save_path = './checkpoint/mnist.ckpt'

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

model.load_weights(model_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)