欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

【北京大学】Tensorflow2.0第四讲

程序员文章站 2022-07-13 12:47:49
...

1 本讲目标

(1)自制数据集,解决本领域应用
(2)数据增强,扩充数据集
(3)断点续训,存取模型
(4)参数提取,把参数存入文本
(5)acc/loss 可视化,查看训练效果
(6)应用程序,给图识物

2 自制数据集

(1) 观察数据集数据结构,给x_train、y_train 、x_test、y_test

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8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_
    ```
# 3 数据增强
```python
image_gen_train = ImageDataGenerator(
    rescale=1. / 255,# 所有数据将乘以该数值
    rotation_range=45, # 随机旋转角度范围
    width_shift_range=.15,# 随机宽度偏移量
    height_shift_range=.15, # 随机高度偏移量
    horizontal_flip=False,# 是否随机水平翻转
    zoom_range=0.5  # 随机缩放的范围[1-n.1+n]
)
image_gen_train.fit(x_train)

4 断点续训 存取模型

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(),
    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'])
# 读取模型load_weights(路径文件名)
checkpoint_save_path = "./checkpoint/mnist.ckpt"# 生成ckpt文件的时候,会产生相应的索引表
if os.path.exists(checkpoint_save_path + '.index'):# 通过判断是否有索引表,去判断是否保存过模型的参数
    print('-------------load the model-----------------')
    model.load_weights(checkpoint_save_path)# 读取模型参数
# 保存模型: 
cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
                                                 save_weights_only=True,# 是否只保留模型参数
                                                 save_best_only=True)# 是否只保留最有结果
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()

5 参数提取

(1)提取可训练参数
model.trainable_variables返回模型中可训练的参数
(2)设置print输出格式
np.set_printoptions(threshold = 超过多少省略显示)

np.set_printoptions(threshold=np.inf)#np.inf无限大
# 把可训练参数存入文件
print(model.trainable_variables)
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()

6 acc/loss可视化,查看训练效果

(1)使用方法
history = model.fit(训练集数据,训练集标签,batch_size = ,epochs = ,validation_split =用作测试数据的比例,validation_data = 测试集,validation_freq = 测试频率)
(2)可选参数
history:
训练集loss: loss
测试集loss: val_los
训练集准确率:sparse_categorical_accuracy
测试集准确率: val_sparse_categorical_accuracy

# 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()

(3)完整Demo

import tensorflow as tf
import os
import numpy as np
from matplotlib import pyplot as plt
np.set_printoptions(threshold=np.inf)
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'])
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)
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()
###############################################    show   ###############################################
# 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()

7 应用程序给图识物

(1)前向传播执行应用
predict(输入特征,batch_size = 整数)
返回前向传播计算结果
(2)复现模型(前向传播)

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

(3)加载参数(读取参数)

model.load_weights(model_save_path)

(4)预测结果

result = model.predict(x_predict)

(5)图片预处理

# 图片预处理
    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
# 图片归一化
    img_arr = img_arr / 255.0
 

(6)完整Demo

from PIL import Image
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
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)
    image = plt.imread(image_path)
    plt.set_cmap('gray')
    plt.imshow(image)
    img = img.resize((28, 28), Image.ANTIALIAS)
    img_arr = np.array(img.convert('L'))
    # 图片预处理
    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
    # 将(28,28)的二维数据变成(1,28,28)的三维数据
    x_predict = img_arr[tf.newaxis, ...]
    result = model.predict(x_predict)
    pred = tf.argmax(result, axis=1)
    print('\n')
    tf.print(pred)
    plt.pause(1)
    plt.close()
    ```