1.TFRecord简介

1）TFRecord是什么

TFRecord --> Example --> feature --> key-value键值对，并且value的取值有三种

2）为什么用TFRecord

为什么要用TFRecord？

3）TFRecord格式

2.写入TFRecord

3.读取TFRecord文件

4.案例实战-猫狗图片分类

import tensorflow as tf
import os# 处理文件路径
data_dir = 'datasets'train_cats_dir = data_dir + '/train/cats/'
train_dogs_dir = data_dir + '/train/dogs/'train_tfrecord_file = data_dir + '/train/train.tfrecords'test_cats_dir = data_dir + '/valid/cats/'
test_dogs_dir = data_dir + '/valid/dogs/'test_tfrecord_file = data_dir + '/valid/test.tfrecords'# 将数据存储为TFRecord文件# 文件名字变成list
train_cat_filenames = [train_cats_dir + filename for filename in os.listdir(train_cats_dir)]
train_dog_filenames = [train_dogs_dir + filename for filename in os.listdir(train_dogs_dir)]
train_filenames = train_cat_filenames + train_dog_filenames# 将猫类的标签设为0，dog类的标签设为1
train_labels = [0] * len(train_cat_filenames) + [1] * len(train_dog_filenames)# 写入TFRcord文件
with tf.io.TFRecordWriter(train_tfrecord_file) as writer:for filename, label in zip(train_filenames,train_labels):# 读取数据集图片到内存，image为一个byte类型的字符串image = open(filename,'rb').read()# 建立tf.train.Feature字典feature = {'image' : tf.train.Feature(bytes_list = tf.train.BytesList(value=[image])),    # 图片是一个Bytes对象'label' : tf.train.Feature(int64_list = tf.train.Int64List(value=[label]))     # 标签是一个Int对象}# 通过字典建立Exampleexample = tf.train.Example(features=tf.train.Features(feature=feature))# 将Example序列化serialized = example.SerializeToString()# 写入TFRecord文件writer.write(serialized)test_cat_filenames = [test_cats_dir + filename for filename in os.listdir(test_cats_dir)]
test_dog_filenames = [test_dogs_dir + filename for filename in os.listdir(test_dogs_dir)]
test_filenames = test_cat_filenames + test_dog_filenames# 将猫类的标签设为0，dog类的标签设为1
test_labels = [0] * len(test_cat_filenames) + [1] * len(test_dog_filenames)  
with tf.io.TFRecordWriter(test_tfrecord_file) as writer:for filename, label in zip(test_filenames, test_labels):image = open(filename, 'rb').read()     # 读取数据集图片到内存，image 为一个 Byte 类型的字符串feature = {                             # 建立 tf.train.Feature 字典'image': tf.train.Feature(bytes_list=tf.train.BytesList(value=[image])),  # 图片是一个 Bytes 对象'label': tf.train.Feature(int64_list=tf.train.Int64List(value=[label]))   # 标签是一个 Int 对象}example = tf.train.Example(features=tf.train.Features(feature=feature)) # 通过字典建立 Exampleserialized = example.SerializeToString() #将Example序列化writer.write(serialized)   # 写入 TFRecord 文件# 读取TFRecord文件# 定义Feature结构，告诉解码器每个Feature的类型是什么
feature_description = {'image': tf.io.FixedLenFeature([],tf.string),'label' : tf.io.FixedLenFeature([],tf.int64),
}# 定义解码函数
def _parse_example(example_string):# 将TFRecord文件中的每一个序列化的tf.train.Example解码feature_dict = tf.io.parse_single_example(example_string, feature_description)# 解码JPEG图片feature_dict['image'] = tf.io.decode_jpeg(feature_dict['image'])   # 处理大小与像素feature_dict['image'] = tf.image.resize(feature_dict['image'],[256, 256]) / 255.0return feature_dict['image'], feature_dict['label']batch_size = 32# 读取TFRecord文件
train_dataset = tf.data.TFRecordDataset(train_tfrecord_file)# 解码
train_dataset = train_dataset.map(_parse_example)
for image,label in train_dataset.take(1):print(image.shape,label)
# (256, 256, 3) tf.Tensor(0, shape=(), dtype=int64)# 模型批量读取
train_dataset = train_dataset.shuffle(buffer_size = 23000)
train_dataset = train_dataset.batch(batch_size)
# (32,256,256,3)
# 优化
train_dataset = train_dataset.prefetch(tf.data.experimental.AUTOTUNE)# 测试集的读取
test_dataset = tf.data.TFRecordDataset(test_tfrecord_file)
test_dataset = test_dataset.map(_parse_example)
test_dataset = test_dataset.batch(batch_size)# 定义CNN模型
class CNNModel(tf.keras.models.Model):def __init__(self):super(CNNModel,self).__init__()self.conv1 = tf.keras.layers.Conv2D(32,3,activation='relu')self.maxpool1 = tf.keras.layers.MaxPooling2D()self.conv2 = tf.keras.layers.Conv2D(32,5,activation='relu')self.maxpool2 = tf.keras.layers.MaxPooling2D()self.flatten = tf.keras.layers.Flatten()self.d1 = tf.keras.layers.Dense(64,activation='relu')self.d2 = tf.keras.layers.Dense(2,activation='softmax')def call(self,x):# 定义前向传播x = self.conv1(x)x = self.maxpool1(x)x = self.conv2(x)x = self.maxpool2(x)x = self.flatten(x)x = self.d1(x)x = self.d2(x)return xlearning_rate = 0.001
model = CNNModel()loss_object = tf.keras.losses.SparseCategoricalCrossentropy()
optimizer = tf.keras.optimizers.Adam(learning_rate)# 损失与评估
train_loss = tf.keras.metrics.Mean(name = 'train_loss')
train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name = 'test_accuracy')# batch
# 将动态图转换为静态图，静态图执行效率高
@tf.function
def train_step(images,labels):with tf.GradientTape() as tape:predictions = model(images)loss = loss_object(labels,predictions)# 计算梯度gradients = tape.gradient(loss,model.trainable_variables)optimizer.apply_gradients(zip(gradients,model.trainable_variables))train_loss(loss)train_accuracy(labels,predictions)  # update@tf.function
def test_step(images,labels):predictions = model(images)t_loss = loss_object(labels,predictions)test_loss(t_loss)test_accuracy(labels,predictions)# 模型训练
EPOCHS = 10for epoch in range(EPOCHS):# 重置评估指标train_loss.reset_states()train_accuracy.reset_states()test_loss.reset_states()test_accuracy.reset_states()for images,labels in train_dataset:train_step(images,labels)for test_images,test_labels in test_dataset:test_step(images,labels)template = 'Epoch {}, Loss : {}, Accuracy : {},Test Loss : {},Test Accuracy : {}'# 打印print(template.format(epoch + 1,train_loss.result(),train_accuracy.result() * 100,test_loss.result(),test_accuracy.result() * 100))