import tensorflow as tf
from PIL import Image
import numpy as np
import os
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from matplotlib import pyplot as plt
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_
print('-------------Generate Datasets-----------------')
x_train, y_train = generateds(train_path, train_txt)
x_test, y_test = generateds(test_path, test_txt)
x_train=x_train.reshape(x_train.shape[0],28,28,1)#给数据增加一个维度,从(60000,28,28)到(60000,28,28,1)
######数据增强,扩充数据集
image_gen_train=ImageDataGenerator(
rescale=1. / 255.,#如为图像,分母为255时,可归一到0~1
rotation_range=45,#随机45度旋转
width_shift_range=.15, # 宽度偏移
height_shift_range=.15,#高度偏移量
horizontal_flip=False,#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)
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,存储模型
checkpoint_save_path="./checkpoint/mnist.ckpt"
if os.path.exists(checkpoint_save_path+'.index'):
print('------load the model------')
model.load_weights(checkpoint_save_path)
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()
######参数提取,把参数存入文本
print(model.trainable_variables)#返回模型中可训练的参数
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()
# 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()