目录

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

  1. def generateds(path, txt):
  2. f = open(txt, 'r') # 以只读形式打开txt文件
  3. contents = f.readlines() # 读取文件中所有行
  4. f.close() # 关闭txt文件
  5. x, y_ = [], [] # 建立空列表
  6. for content in contents: # 逐行取出
  7. value = content.split() # 以空格分开,图片路径为value[0] , 标签为value[1] , 存入列表
  8. img_path = path + value[0] # 拼出图片路径和文件名
  9. img = Image.open(img_path) # 读入图片
  10. img = np.array(img.convert('L')) # 图片变为8位宽灰度值的np.array格式
  11. img = img / 255. # 数据归一化 (实现预处理)
  12. x.append(img) # 归一化后的数据,贴到列表x
  13. y_.append(value[1]) # 标签贴到列表y_
  14. print('loading : ' + content) # 打印状态提示
  15. x = np.array(x) # 变为np.array格式
  16. y_ = np.array(y_) # 变为np.array格式
  17. y_ = y_.astype(np.int64) # 变为64位整型
  18. return x, y_ # 返回输入特征x,返回标签y_

3 数据增强

  1. image_gen_train = ImageDataGenerator(
  2. rescale=1. / 255,# 所有数据将乘以该数值
  3. rotation_range=45, # 随机旋转角度范围
  4. width_shift_range=.15,# 随机宽度偏移量
  5. height_shift_range=.15, # 随机高度偏移量
  6. horizontal_flip=False,# 是否随机水平翻转
  7. zoom_range=0.5 # 随机缩放的范围[1-n.1+n]
  8. )
  9. 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
image.png

# 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()