人工智能实践：Tensorflow笔记（4）——网络八股扩展
文章目录
- 1、tf.keras搭建神经网络八股
- 2、自制数据集
- 3、数据增强
- 4、断点续训
- 5、参数提取
- 6、acc&loss可视化
- 7、给图识物
1、tf.keras搭建神经网络八股
六步法
import
train,test
Sequential/Class
model.compile
model.fit
model.summary
神经网络训练的目的，就是获取各层网络最优的参数
- 自制数据集，解决本领域问题
- 数据增强，扩充数据集
- 断点续训，存取模型
- 参数提取，把参数存入文本
- acc/loss可视化，查看训练效果
- 应用程序，给图识物
2、自制数据集
观察数据集数据结构，给x_train、y_train、x_test、y_test赋值
黑底白字的灰度图，每张图有28行28列个像素点，每个像素点都是0到255之间的整数，纯黑色用数值0表示，纯白色用数值255表示
def generateds(图片路径,标签文件)
把图片路径作为第一参数，标签文件作为第二参数
目标：把图片路径和标签文件输入genrateds()函数
拿到本地数据集，首先要观察数据集的结构，txt文件中有两列，第一列是图片名，第二列是对应的标签，value[0]这一列用于索引到每张图片，value[1]为每张图片对应的标签，只需把图片灰度值数据拼接到图片列表，把标签数据拼接到标签列表，顺序一致就OK
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x，y_
for content in contents: #逐行读出
value = content.split() #以空格分开
img_path = path + value[0]
img = Image.open(img_path) #读入图片
img = np.array(img.convert('L')) #图片变为8位宽度的灰度值
img = img / 255. #数据归一化
x.append(img)
y_.append(value[1])
print('loading : ' + content)
x = np.array(x)
y_ = np.array(y_)
y_ = y_.astype(np.int64)
return x,y_
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_
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)
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'])
model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()
3、数据增强
数据增强可以帮助扩展数据集，对图像的增强就是对图像的简单形变，用来应对因拍照角度不同引起的图片变形
数据增强（增大数据集）
image_gen_train = tf.keras.preprocessing.image.ImageDataGenerator(
rescale = 所有数据将乘以该数值 #对输入特征大小进行调整
rotation_range = 随机旋转角度数范围 #对图像进行角度的随机旋转
width_shift_range = 随机宽度偏移量 #对图像进行随机宽度偏移
height_shift_range = 随机高度偏移量 #对图像进行随机高度偏移
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]) #选择按照什么比例随机缩小放大图片
image_gen_train.fit(x_train)
例：
image_gen_train = 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 = False, #水平翻转
zoom_range = 0.5 #将图像随机缩放阈量50%）
image_gen_train.fit(x_train)
image_gen_train.fit(x_train)这里的fit需要输入一个四维数据，所以要对x_train进行reshape，把60000张28行28列数据，变为60000张28行28列单通道数据，这个单通道为灰度值
model.fit同步更新为.flow形式，把训练集输入特征x_train、训练集标签y_train，按照batch打包送入model.fit执行训练过程
import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator
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,从(60000, 28, 28)reshape为(60000, 28, 28, 1)
image_gen_train = 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=False, # 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(),
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'])
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()
from tensorflow.keras.utils import get_file
import gzip
import numpy as np
def load_data():
base = "file:///D:/AI/class3/"
files = ['train-labels-idx1-ubyte.gz','train-images-idx3-ubyte.gz',
't10k-labels-idx1-ubyte.gz','t10k-images-idx3-ubyte.gz'
]
paths = []
for fname in files:
paths.append(get_file(fname,origin = base + fname))
with gzip.open(paths[0], 'rb') as lbpath:
y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[1], 'rb') as imgpath:
x_train = np.frombuffer(
imgpath.read(), np.uint8, offset=16).reshape(len(y_train), 28, 28)
with gzip.open(paths[2], 'rb') as lbpath:
y_test = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[3], 'rb') as imgpath:
x_test = np.frombuffer(
imgpath.read(), np.uint8, offset=16).reshape(len(y_test), 28, 28)
return (x_train, y_train), (x_test, y_test)
import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import LoadData
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = LoadData.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,从(60000, 28, 28)reshape为(60000, 28, 28, 1)
image_gen_train = 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=False, # 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(),
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'])
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()
随着模型迭代轮数的增加，模型准确率不断提高，数据增强在小数据量上，可以增加模型泛化性，在实际应用模型时能体现出效果
4、断点续训
断点续训可以存取模型
读取模型：
load_weights(路径文件名)
checkpoint_save_path = "./checkpoint/mnist.ckpt"
if os.path.exists(checkpoint_save_path + '.index'):
print('----------load the model----------')
model.load_weights(checkpoint_save_path)
保存模型：(使用TensorFlow给出的回调函数)
tf.keras.callbacks.ModelCheckpoint(
filepath = 路径文件名,
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]) #加入callbacks选项
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])
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'])
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()
在训练过程中出现了checkpoint文件夹，里面存放模型的参数，再次运行，这次运行的准确率是在刚刚保存模型的基础上继续提升的
5、参数提取
把参数存入文本
提取可训练参数
model.trainable_variables返回模型中可训练的参数
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表示无限大
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()
在断点续训的基础上加入了参数提取功能
import tensorflow as tf
import os
import numpy as np
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()
6、acc&loss可视化
acc曲线与loss曲线
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)
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']
#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 Vaildation Accuracy')
plt.legend()
plt.subplot(1,2,2)
plt.plot(loss,label='Training Loss')
plt.plot(val_loss,label='Vaildation Loss')
plt.title('Training and Validation Loss')
plt.legend()
plt.show()
在断点续训和参数提取代码的基础上，加入了画图模块plt和几行画图程序
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、给图识物
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
#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')])
#加载参数
model.load_weights(model_save_path)
#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'))
img_arr = 255 - img_arr
img_arr = img_arr / 255.0
print("img_arr:",img_arr.shape)
x_predict = img_arr[tf.newaxis, ...]
print("x_predict:",x_predict.shape)
result = model.predict(x_predict)
pred = tf.argmax(result, axis=1)
print('\n')
tf.print(pred)
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'))
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)
plt.pause(1)
plt.close()