详解TensorFlow训练网络两种方式
作者:学姐带你玩AI 时间:2021-06-24 00:18:23
TensorFlow训练网络有两种方式,一种是基于tensor(array),另外一种是迭代器
两种方式区别是:
第一种是要加载全部数据形成一个tensor,然后调用model.fit()然后指定参数batch_size进行将所有数据进行分批训练
第二种是自己先将数据分批形成一个迭代器,然后遍历这个迭代器,分别训练每个批次的数据
方式一:通过迭代器
IMAGE_SIZE = 1000
# step1:加载数据集
(train_images, train_labels), (val_images, val_labels) = tf.keras.datasets.mnist.load_data()
# step2:将图像归一化
train_images, val_images = train_images / 255.0, val_images / 255.0
# step3:设置训练集大小
train_images = train_images[:IMAGE_SIZE]
val_images = val_images[:IMAGE_SIZE]
train_labels = train_labels[:IMAGE_SIZE]
val_labels = val_labels[:IMAGE_SIZE]
# step4:将图像的维度变为(IMAGE_SIZE,28,28,1)
train_images = tf.expand_dims(train_images, axis=3)
val_images = tf.expand_dims(val_images, axis=3)
# step5:将图像的尺寸变为(32,32)
train_images = tf.image.resize(train_images, [32, 32])
val_images = tf.image.resize(val_images, [32, 32])
# step6:将数据变为迭代器
train_loader = tf.data.Dataset.from_tensor_slices((train_images, train_labels)).batch(32)
val_loader = tf.data.Dataset.from_tensor_slices((val_images, val_labels)).batch(IMAGE_SIZE)
# step5:导入模型
model = LeNet5()
# 让模型知道输入数据的形式
model.build(input_shape=(1, 32, 32, 1))
# 结局Output Shape为 multiple
model.call(Input(shape=(32, 32, 1)))
# step6:编译模型
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
# 权重保存路径
checkpoint_path = "./weight/cp.ckpt"
# 回调函数,用户保存权重
save_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,
save_best_only=True,
save_weights_only=True,
monitor='val_loss',
verbose=0)
EPOCHS = 11
for epoch in range(1, EPOCHS):
# 每个批次训练集误差
train_epoch_loss_avg = tf.keras.metrics.Mean()
# 每个批次训练集精度
train_epoch_accuracy = tf.keras.metrics.SparseCategoricalAccuracy()
# 每个批次验证集误差
val_epoch_loss_avg = tf.keras.metrics.Mean()
# 每个批次验证集精度
val_epoch_accuracy = tf.keras.metrics.SparseCategoricalAccuracy()
for x, y in train_loader:
history = model.fit(x,
y,
validation_data=val_loader,
callbacks=[save_callback],
verbose=0)
# 更新误差,保留上次
train_epoch_loss_avg.update_state(history.history['loss'][0])
# 更新精度,保留上次
train_epoch_accuracy.update_state(y, model(x, training=True))
val_epoch_loss_avg.update_state(history.history['val_loss'][0])
val_epoch_accuracy.update_state(next(iter(val_loader))[1], model(next(iter(val_loader))[0], training=True))
# 使用.result()计算每个批次的误差和精度结果
print("Epoch {:d}: trainLoss: {:.3f}, trainAccuracy: {:.3%} valLoss: {:.3f}, valAccuracy: {:.3%}".format(epoch,
train_epoch_loss_avg.result(),
train_epoch_accuracy.result(),
val_epoch_loss_avg.result(),
val_epoch_accuracy.result()))
方式二:适用model.fit()进行分批训练
import model_sequential
(train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.mnist.load_data()
# step2:将图像归一化
train_images, test_images = train_images / 255.0, test_images / 255.0
# step3:将图像的维度变为(60000,28,28,1)
train_images = tf.expand_dims(train_images, axis=3)
test_images = tf.expand_dims(test_images, axis=3)
# step4:将图像尺寸改为(60000,32,32,1)
train_images = tf.image.resize(train_images, [32, 32])
test_images = tf.image.resize(test_images, [32, 32])
# step5:导入模型
# history = LeNet5()
history = model_sequential.LeNet()
# 让模型知道输入数据的形式
history.build(input_shape=(1, 32, 32, 1))
# history(tf.zeros([1, 32, 32, 1]))
# 结局Output Shape为 multiple
history.call(Input(shape=(32, 32, 1)))
history.summary()
# step6:编译模型
history.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
# 权重保存路径
checkpoint_path = "./weight/cp.ckpt"
# 回调函数,用户保存权重
save_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,
save_best_only=True,
save_weights_only=True,
monitor='val_loss',
verbose=1)
# step7:训练模型
history = history.fit(train_images,
train_labels,
epochs=10,
batch_size=32,
validation_data=(test_images, test_labels),
callbacks=[save_callback])
来源:https://blog.csdn.net/m0_47256162/article/details/122179151
标签:TensorFlow,训练网络
0
投稿
猜你喜欢
Centos7 mysql数据库安装及配置实现教程
2024-01-16 06:39:40
Laravel框架实现利用监听器进行sql语句记录功能
2024-05-13 09:53:49
用我喜欢的字体(Cufon)
2009-12-11 18:51:00
浅谈PyQt5中异步刷新UI和Python多线程总结
2023-08-22 01:37:18
Python数组条件过滤filter函数使用示例
2021-06-11 15:10:51
在Windows下安装配置CPU版的PyTorch的方法
2023-07-18 15:04:17
一文弄懂什么是MySQL的回表
2024-01-22 16:56:56
sqlserver 文件数据库和关系数据库的比较
2011-10-24 20:11:38
Python脚本实现Zabbix多行日志监控过程解析
2021-12-27 09:40:47
asp 小偷采集程序原理与常用函数方法
2011-03-06 10:36:00
Python设计模式之代理模式实例详解
2022-11-20 05:24:29
PHP页面中文乱码分析
2024-05-13 09:23:19
用蜜罐来阻止垃圾评论
2007-11-06 12:35:00
使用python实现个性化词云的方法
2021-08-27 03:46:59
PHP实现获取两个以逗号分割的字符串的并集
2023-06-01 03:24:53
使用Python中Tkinter模块的Treeview 组件显示ini文件操作
2022-05-23 03:45:38
MySQL如何设置某个字段的值自增
2024-01-27 09:49:09
Vue配置文件vue.config.js配置前端代理方式
2023-07-02 16:39:06
javascript解锁前端密码框常见功能做法
2024-04-16 10:36:33
Django实现简单分页功能的方法详解
2021-02-07 01:54:23