一、自制数据集,应对特定应用
首先需要有4个文件夹
-
训练集图片
-
训练集标签
-
测试集图片
-
测试集标签
测试代码如下:增加了自制数据集的处理过程,其余代码与笔记2中一样
#自制数据集
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'
#(输入特征路径,标签路径文件名)
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_
#如果之前已经读取过就直接调用,没有读取过则执行读取操作,再将结果保存为 .npy文件以备下次使用
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()
二、数据增强,加大数据量
常用增强方法:
keras.preprocessing.image.ImageDataGenerator(
featurewise_center=False, #输入值按照均值为0进行处理
samplewise_center=False, #每个样本的均值按0处理
featurewise_std_normalization=False, #输入值按照标准正态化处理
samplewise_std_normalization=False, #每个样本按照标准正态化处理
zca_whitening=False, # 是否开启增白
zca_epsilon=1e-06,
rotation_range=0, #图像随机旋转一定角度,最大旋转角度为设定值
width_shift_range=0.0, #图像随机水平平移,最大平移值为设定值。若值为小于1的float值,则可认为是按比例平移,若大于1,则平移的是像素;若值为整型,平移的也是像素;假设像素为2.0,则移动范围为[-1,1]之间
height_shift_range=0.0, #图像随机垂直平移,同上
brightness_range=None, # 图像随机亮度增强,给定一个含两个float值的list,亮度值取自上下限值间
shear_range=0.0, # 图像随机修剪
zoom_range=0.0, # 图像随机变焦
channel_shift_range=0.0,
fill_mode=‘nearest’, #填充模式,默认为最近原则,比如一张图片向右平移,那么最左侧部分会被临近的图案覆盖
cval=0.0,
horizontal_flip=False, #图像随机水平翻转
vertical_flip=False, #图像随机垂直翻转
rescale=None, #缩放尺寸
preprocessing_function=None,
data_format=None,
validation_split=0.0,
dtype=None)
例:
image_gen_train = ImageDataGenerator(
rescale=1./255, #原像素值 0~255 归至 0~1
rotation_range=45, #随机 45 度旋转
width_shift_range=.15, #随机宽度偏移 [-0.15,0.15)
height_shift_range=.15, #随机高度偏移 [-0.15,0.15)
horizontal_flip=True, #随机水平翻转
zoom_range=0.5 #随机缩放到 [1-50%,1+50%]
)
image_gen_train.fit(x_train)
代码如下:
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()
注:
- model.fit(x_train,y_train,batch_size=32,……)变为
model.fit(image_gen_train.flow(x_train, y_train,batch_size=32), ……) - 数据增强函数的输入要求是 4 维,通过 reshape 调整
三、断点续训,存取模型
每次训练结束后保留最优模型,下次训练接着上次保存的模型继续训练
#断点续训
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
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)
#将最优模型保存
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()
四、参数提取,写至文本
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()
输出结果:(只有最后一小部分)
五、acc曲线/loss可视化从,查看效果
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()