第四章神经网络拓展
4.1总览
对第三章对6步进行拓展
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
4.2自制数据集
在代码中进行解释
代码实现：
import tensorflow as tf
from PIL import Image
import numpy as np
import os
train_path = './fashion_image_label/fashion_train_jpg_60000/' # 训练集图片路径
train_txt = './fashion_image_label/fashion_train_jpg_60000.txt' # 训练集标签文件
x_train_savepath = './fashion_image_label/fashion_x_train.npy' # 特征存储文件
y_train_savepath = './fashion_image_label/fahion_y_train.npy' # 标签存储文件
test_path = './fashion_image_label/fashion_test_jpg_10000/'
test_txt = './fashion_image_label/fashion_test_jpg_10000.txt'
x_test_savepath = './fashion_image_label/fashion_x_test.npy'
y_test_savepath = './fashion_image_label/fashion_y_test.npy'
def generateds(path, txt):
f = open(txt, 'r')
contents = f.readlines() # 按行读取
f.close()
x, y_ = [], []
for content in contents:
value = content.split() # 以空格分开，存入数组
img_path = path + value[0]
img = Image.open(img_path)
img = np.array(img.convert('L')) # 图片变为np格式
img = img / 255.
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_
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()
4.3数据增强
image_gen_train = tf.keras.preprocessing.image.ImageDataGenerator(
rescale = 所有数据将乘以该数值
rotation_range = 随机旋转角度数范围
width_shift_range = 随机宽度偏移量
height_shift_range = 随机高度偏移量
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] )
image_gen_train.fit(x_train)
import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator
fashion = tf.keras.datasets.fashion_mnist
(x_train, y_train), (x_test, y_test) = fashion.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，使数据和网络结构匹配
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=True, # 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()
4.4断点续训
读取保存模型
读取模型:
load_weights(路径文件名)
checkpoint_save_path = "./checkpoint/fashion.ckpt"
if os.path.exists(checkpoint_save_path + '.index'):
print('-------------load the model-----------------')
model.load_weights(checkpoint_save_path)
保存模型:
tf.keras.callbacks.ModelCheckpoint( filepath=路径文件名,
save_weights_only=True/False,
save_best_only=True/False)
history = model.fit( callbacks=[cp_callback] )
import tensorflow as tf
import os
fashion = tf.keras.datasets.fashion_mnist
(x_train, y_train), (x_test, y_test) = fashion.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/fashion.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, # 是否只保留模型参数
save_best_only=True) # 是否只保留最优结果
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()
4.5参数提取
查看上一节中所保存的参数
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) # 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')
4.6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
# 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()
如果使用mac出现OMP: Error #15: Initializing libiomp5.dylib, but found libiomp5.dylib already initialized.加入
import os
os.environ['KMP_DUPLICATE_LIB_OK']='True'
就可以解决无法作图的问题了。
4.7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
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)
下面给出代码：
from PIL import Image
import numpy as np
import tensorflow as tf
type = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
model_save_path = './checkpoint/fashion.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 #每个像素点= 255 - 各自点当前灰度值
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')
print(type[int(pred)])