TensorFlow2.0使用keras训练模型的实现


Posted in Python onFebruary 20, 2021

1.一般的模型构造、训练、测试流程

# 模型构造
inputs = keras.Input(shape=(784,), name='mnist_input')
h1 = layers.Dense(64, activation='relu')(inputs)
h1 = layers.Dense(64, activation='relu')(h1)
outputs = layers.Dense(10, activation='softmax')(h1)
model = keras.Model(inputs, outputs)
# keras.utils.plot_model(model, 'net001.png', show_shapes=True)

model.compile(optimizer=keras.optimizers.RMSprop(),
    loss=keras.losses.SparseCategoricalCrossentropy(),
    metrics=[keras.metrics.SparseCategoricalAccuracy()])

# 载入数据
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
x_train = x_train.reshape(60000, 784).astype('float32') /255
x_test = x_test.reshape(10000, 784).astype('float32') /255

x_val = x_train[-10000:]
y_val = y_train[-10000:]

x_train = x_train[:-10000]
y_train = y_train[:-10000]

# 训练模型
history = model.fit(x_train, y_train, batch_size=64, epochs=3,
   validation_data=(x_val, y_val))
print('history:')
print(history.history)

result = model.evaluate(x_test, y_test, batch_size=128)
print('evaluate:')
print(result)
pred = model.predict(x_test[:2])
print('predict:')
print(pred)

2.自定义损失和指标

自定义指标只需继承Metric类, 并重写一下函数

_init_(self),初始化。

update_state(self,y_true,y_pred,sample_weight = None),它使用目标y_true和模型预测y_pred来更新状态变量。

result(self),它使用状态变量来计算最终结果。

reset_states(self),重新初始化度量的状态。

# 这是一个简单的示例,显示如何实现CatgoricalTruePositives指标,该指标计算正确分类为属于给定类的样本数量

class CatgoricalTruePostives(keras.metrics.Metric):
 def __init__(self, name='binary_true_postives', **kwargs):
  super(CatgoricalTruePostives, self).__init__(name=name, **kwargs)
  self.true_postives = self.add_weight(name='tp', initializer='zeros')
  
 def update_state(self, y_true, y_pred, sample_weight=None):
  y_pred = tf.argmax(y_pred)
  y_true = tf.equal(tf.cast(y_pred, tf.int32), tf.cast(y_true, tf.int32))
  
  y_true = tf.cast(y_true, tf.float32)
  
  if sample_weight is not None:
   sample_weight = tf.cast(sample_weight, tf.float32)
   y_true = tf.multiply(sample_weight, y_true)
   
  return self.true_postives.assign_add(tf.reduce_sum(y_true))
 
 def result(self):
  return tf.identity(self.true_postives)
 
 def reset_states(self):
  self.true_postives.assign(0.)
  

model.compile(optimizer=keras.optimizers.RMSprop(1e-3),
    loss=keras.losses.SparseCategoricalCrossentropy(),
    metrics=[CatgoricalTruePostives()])

model.fit(x_train, y_train,
   batch_size=64, epochs=3)
# 以定义网络层的方式添加网络loss
class ActivityRegularizationLayer(layers.Layer):
 def call(self, inputs):
  self.add_loss(tf.reduce_sum(inputs) * 0.1)
  return inputs

inputs = keras.Input(shape=(784,), name='mnist_input')
h1 = layers.Dense(64, activation='relu')(inputs)
h1 = ActivityRegularizationLayer()(h1)
h1 = layers.Dense(64, activation='relu')(h1)
outputs = layers.Dense(10, activation='softmax')(h1)
model = keras.Model(inputs, outputs)
# keras.utils.plot_model(model, 'net001.png', show_shapes=True)

model.compile(optimizer=keras.optimizers.RMSprop(),
    loss=keras.losses.SparseCategoricalCrossentropy(),
    metrics=[keras.metrics.SparseCategoricalAccuracy()])
model.fit(x_train, y_train, batch_size=32, epochs=1)
# 也可以以定义网络层的方式添加要统计的metric
class MetricLoggingLayer(layers.Layer):
 def call(self, inputs):
  self.add_metric(keras.backend.std(inputs),
      name='std_of_activation',
      aggregation='mean')
  
  return inputs

inputs = keras.Input(shape=(784,), name='mnist_input')
h1 = layers.Dense(64, activation='relu')(inputs)
h1 = MetricLoggingLayer()(h1)
h1 = layers.Dense(64, activation='relu')(h1)
outputs = layers.Dense(10, activation='softmax')(h1)
model = keras.Model(inputs, outputs)
# keras.utils.plot_model(model, 'net001.png', show_shapes=True)

model.compile(optimizer=keras.optimizers.RMSprop(),
    loss=keras.losses.SparseCategoricalCrossentropy(),
    metrics=[keras.metrics.SparseCategoricalAccuracy()])
model.fit(x_train, y_train, batch_size=32, epochs=1)
# 也可以直接在model上面加
# 也可以以定义网络层的方式添加要统计的metric
class MetricLoggingLayer(layers.Layer):
 def call(self, inputs):
  self.add_metric(keras.backend.std(inputs),
      name='std_of_activation',
      aggregation='mean')
  
  return inputs

inputs = keras.Input(shape=(784,), name='mnist_input')
h1 = layers.Dense(64, activation='relu')(inputs)
h2 = layers.Dense(64, activation='relu')(h1)
outputs = layers.Dense(10, activation='softmax')(h2)
model = keras.Model(inputs, outputs)

model.add_metric(keras.backend.std(inputs),
      name='std_of_activation',
      aggregation='mean')
model.add_loss(tf.reduce_sum(h1)*0.1)

# keras.utils.plot_model(model, 'net001.png', show_shapes=True)

model.compile(optimizer=keras.optimizers.RMSprop(),
    loss=keras.losses.SparseCategoricalCrossentropy(),
    metrics=[keras.metrics.SparseCategoricalAccuracy()])
model.fit(x_train, y_train, batch_size=32, epochs=1)

处理使用validation_data传入测试数据,还可以使用validation_split划分验证数据

ps:validation_split只能在用numpy数据训练的情况下使用

model.fit(x_train, y_train, batch_size=32, epochs=1, validation_split=0.2)

3.使用tf.data构造数据

def get_compiled_model():
 inputs = keras.Input(shape=(784,), name='mnist_input')
 h1 = layers.Dense(64, activation='relu')(inputs)
 h2 = layers.Dense(64, activation='relu')(h1)
 outputs = layers.Dense(10, activation='softmax')(h2)
 model = keras.Model(inputs, outputs)
 model.compile(optimizer=keras.optimizers.RMSprop(),
     loss=keras.losses.SparseCategoricalCrossentropy(),
     metrics=[keras.metrics.SparseCategoricalAccuracy()])
 return model
model = get_compiled_model()
train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
train_dataset = train_dataset.shuffle(buffer_size=1024).batch(64)

val_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val))
val_dataset = val_dataset.batch(64)

# model.fit(train_dataset, epochs=3)
# steps_per_epoch 每个epoch只训练几步
# validation_steps 每次验证,验证几步
model.fit(train_dataset, epochs=3, steps_per_epoch=100,
   validation_data=val_dataset, validation_steps=3)

4.样本权重和类权重

“样本权重”数组是一个数字数组,用于指定批处理中每个样本在计算总损失时应具有多少权重。 它通常用于不平衡的分类问题(这个想法是为了给予很少见的类更多的权重)。 当使用的权重是1和0时,该数组可以用作损失函数的掩码(完全丢弃某些样本对总损失的贡献)。

“类权重”dict是同一概念的更具体的实例:它将类索引映射到应该用于属于该类的样本的样本权重。 例如,如果类“0”比数据中的类“1”少两倍,则可以使用class_weight = {0:1.,1:0.5}。

# 增加第5类的权重
import numpy as np
# 样本权重
model = get_compiled_model()
class_weight = {i:1.0 for i in range(10)}
class_weight[5] = 2.0
print(class_weight)
model.fit(x_train, y_train,
   class_weight=class_weight,
   batch_size=64,
   epochs=4)
# 类权重
model = get_compiled_model()
sample_weight = np.ones(shape=(len(y_train),))
sample_weight[y_train == 5] = 2.0
model.fit(x_train, y_train,
   sample_weight=sample_weight,
   batch_size=64,
   epochs=4)
# tf.data数据
model = get_compiled_model()

sample_weight = np.ones(shape=(len(y_train),))
sample_weight[y_train == 5] = 2.0

train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train,
             sample_weight))
train_dataset = train_dataset.shuffle(buffer_size=1024).batch(64)

val_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val))
val_dataset = val_dataset.batch(64)

model.fit(train_dataset, epochs=3, )

5.多输入多输出模型

image_input = keras.Input(shape=(32, 32, 3), name='img_input')
timeseries_input = keras.Input(shape=(None, 10), name='ts_input')

x1 = layers.Conv2D(3, 3)(image_input)
x1 = layers.GlobalMaxPooling2D()(x1)

x2 = layers.Conv1D(3, 3)(timeseries_input)
x2 = layers.GlobalMaxPooling1D()(x2)

x = layers.concatenate([x1, x2])

score_output = layers.Dense(1, name='score_output')(x)
class_output = layers.Dense(5, activation='softmax', name='class_output')(x)

model = keras.Model(inputs=[image_input, timeseries_input],
     outputs=[score_output, class_output])
keras.utils.plot_model(model, 'multi_input_output_model.png'
      , show_shapes=True)
# 可以为模型指定不同的loss和metrics
model.compile(
 optimizer=keras.optimizers.RMSprop(1e-3),
 loss=[keras.losses.MeanSquaredError(),
   keras.losses.CategoricalCrossentropy()])

# 还可以指定loss的权重
model.compile(
 optimizer=keras.optimizers.RMSprop(1e-3),
 loss={'score_output': keras.losses.MeanSquaredError(),
   'class_output': keras.losses.CategoricalCrossentropy()},
 metrics={'score_output': [keras.metrics.MeanAbsolutePercentageError(),
        keras.metrics.MeanAbsoluteError()],
    'class_output': [keras.metrics.CategoricalAccuracy()]},
 loss_weight={'score_output': 2., 'class_output': 1.})

# 可以把不需要传播的loss置0
model.compile(
 optimizer=keras.optimizers.RMSprop(1e-3),
 loss=[None, keras.losses.CategoricalCrossentropy()])

# Or dict loss version
model.compile(
 optimizer=keras.optimizers.RMSprop(1e-3),
 loss={'class_output': keras.losses.CategoricalCrossentropy()})

6.使用回 调

Keras中的回调是在训练期间(在epoch开始时,batch结束时,epoch结束时等)在不同点调用的对象,可用于实现以下行为:

  • 在培训期间的不同时间点进行验证(超出内置的每个时期验证)
  • 定期检查模型或超过某个精度阈值
  • 在训练似乎平稳时改变模型的学习率
  • 在训练似乎平稳时对顶层进行微调
  • 在培训结束或超出某个性能阈值时发送电子邮件或即时消息通知等等。

可使用的内置回调有

  • ModelCheckpoint:定期保存模型。
  • EarlyStopping:当训练不再改进验证指标时停止培训。
  • TensorBoard:定期编写可在TensorBoard中显示的模型日志(更多细节见“可视化”)。
  • CSVLogger:将丢失和指标数据流式传输到CSV文件。
  • 等等

6.1回调使用

model = get_compiled_model()

callbacks = [
 keras.callbacks.EarlyStopping(
  # Stop training when `val_loss` is no longer improving
  monitor='val_loss',
  # "no longer improving" being defined as "no better than 1e-2 less"
  min_delta=1e-2,
  # "no longer improving" being further defined as "for at least 2 epochs"
  patience=2,
  verbose=1)
]
model.fit(x_train, y_train,
   epochs=20,
   batch_size=64,
   callbacks=callbacks,
   validation_split=0.2)
# checkpoint模型回调
model = get_compiled_model()
check_callback = keras.callbacks.ModelCheckpoint(
 filepath='mymodel_{epoch}.h5',
 save_best_only=True,
 monitor='val_loss',
 verbose=1
)

model.fit(x_train, y_train,
   epochs=3,
   batch_size=64,
   callbacks=[check_callback],
   validation_split=0.2)
# 动态调整学习率
initial_learning_rate = 0.1
lr_schedule = keras.optimizers.schedules.ExponentialDecay(
 initial_learning_rate,
 decay_steps=10000,
 decay_rate=0.96,
 staircase=True
)
optimizer = keras.optimizers.RMSprop(learning_rate=lr_schedule)
# 使用tensorboard
tensorboard_cbk = keras.callbacks.TensorBoard(log_dir='./full_path_to_your_logs')
model.fit(x_train, y_train,
   epochs=5,
   batch_size=64,
   callbacks=[tensorboard_cbk],
   validation_split=0.2)

6.2创建自己的回调方法

class LossHistory(keras.callbacks.Callback):
 def on_train_begin(self, logs):
  self.losses = []
 def on_epoch_end(self, batch, logs):
  self.losses.append(logs.get('loss'))
  print('\nloss:',self.losses[-1])
  
model = get_compiled_model()

callbacks = [
 LossHistory()
]
model.fit(x_train, y_train,
   epochs=3,
   batch_size=64,
   callbacks=callbacks,
   validation_split=0.2)

7.自己构造训练和验证循环

# Get the model.
inputs = keras.Input(shape=(784,), name='digits')
x = layers.Dense(64, activation='relu', name='dense_1')(inputs)
x = layers.Dense(64, activation='relu', name='dense_2')(x)
outputs = layers.Dense(10, activation='softmax', name='predictions')(x)
model = keras.Model(inputs=inputs, outputs=outputs)

# Instantiate an optimizer.
optimizer = keras.optimizers.SGD(learning_rate=1e-3)
# Instantiate a loss function.
loss_fn = keras.losses.SparseCategoricalCrossentropy()

# Prepare the training dataset.
batch_size = 64
train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
train_dataset = train_dataset.shuffle(buffer_size=1024).batch(batch_size)

# 自己构造循环
for epoch in range(3):
 print('epoch: ', epoch)
 for step, (x_batch_train, y_batch_train) in enumerate(train_dataset):
  # 开一个gradient tape, 计算梯度
  with tf.GradientTape() as tape:
   logits = model(x_batch_train)
   
   loss_value = loss_fn(y_batch_train, logits)
   grads = tape.gradient(loss_value, model.trainable_variables)
   optimizer.apply_gradients(zip(grads, model.trainable_variables))
   
  if step % 200 == 0:
   print('Training loss (for one batch) at step %s: %s' % (step, float(loss_value)))
   print('Seen so far: %s samples' % ((step + 1) * 64))
# 训练并验证
# Get model
inputs = keras.Input(shape=(784,), name='digits')
x = layers.Dense(64, activation='relu', name='dense_1')(inputs)
x = layers.Dense(64, activation='relu', name='dense_2')(x)
outputs = layers.Dense(10, activation='softmax', name='predictions')(x)
model = keras.Model(inputs=inputs, outputs=outputs)

# Instantiate an optimizer to train the model.
optimizer = keras.optimizers.SGD(learning_rate=1e-3)
# Instantiate a loss function.
loss_fn = keras.losses.SparseCategoricalCrossentropy()

# Prepare the metrics.
train_acc_metric = keras.metrics.SparseCategoricalAccuracy() 
val_acc_metric = keras.metrics.SparseCategoricalAccuracy()

# Prepare the training dataset.
batch_size = 64
train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
train_dataset = train_dataset.shuffle(buffer_size=1024).batch(batch_size)

# Prepare the validation dataset.
val_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val))
val_dataset = val_dataset.batch(64)


# Iterate over epochs.
for epoch in range(3):
 print('Start of epoch %d' % (epoch,))
 
 # Iterate over the batches of the dataset.
 for step, (x_batch_train, y_batch_train) in enumerate(train_dataset):
 with tf.GradientTape() as tape:
  logits = model(x_batch_train)
  loss_value = loss_fn(y_batch_train, logits)
 grads = tape.gradient(loss_value, model.trainable_variables)
 optimizer.apply_gradients(zip(grads, model.trainable_variables))
  
 # Update training metric.
 train_acc_metric(y_batch_train, logits)

 # Log every 200 batches.
 if step % 200 == 0:
  print('Training loss (for one batch) at step %s: %s' % (step, float(loss_value)))
  print('Seen so far: %s samples' % ((step + 1) * 64))

 # Display metrics at the end of each epoch.
 train_acc = train_acc_metric.result()
 print('Training acc over epoch: %s' % (float(train_acc),))
 # Reset training metrics at the end of each epoch
 train_acc_metric.reset_states()

 # Run a validation loop at the end of each epoch.
 for x_batch_val, y_batch_val in val_dataset:
 val_logits = model(x_batch_val)
 # Update val metrics
 val_acc_metric(y_batch_val, val_logits)
 val_acc = val_acc_metric.result()
 val_acc_metric.reset_states()
 print('Validation acc: %s' % (float(val_acc),))
## 添加自己构造的loss, 每次只能看到最新一次训练增加的loss
class ActivityRegularizationLayer(layers.Layer):
 
 def call(self, inputs):
 self.add_loss(1e-2 * tf.reduce_sum(inputs))
 return inputs
 
inputs = keras.Input(shape=(784,), name='digits')
x = layers.Dense(64, activation='relu', name='dense_1')(inputs)
# Insert activity regularization as a layer
x = ActivityRegularizationLayer()(x)
x = layers.Dense(64, activation='relu', name='dense_2')(x)
outputs = layers.Dense(10, activation='softmax', name='predictions')(x)

model = keras.Model(inputs=inputs, outputs=outputs)
logits = model(x_train[:64])
print(model.losses)
logits = model(x_train[:64])
logits = model(x_train[64: 128])
logits = model(x_train[128: 192])
print(model.losses)
# 将loss添加进求导中
optimizer = keras.optimizers.SGD(learning_rate=1e-3)

for epoch in range(3):
 print('Start of epoch %d' % (epoch,))

 for step, (x_batch_train, y_batch_train) in enumerate(train_dataset):
 with tf.GradientTape() as tape:
  logits = model(x_batch_train)
  loss_value = loss_fn(y_batch_train, logits)

  # Add extra losses created during this forward pass:
  loss_value += sum(model.losses)
  
 grads = tape.gradient(loss_value, model.trainable_variables)
 optimizer.apply_gradients(zip(grads, model.trainable_variables))

 # Log every 200 batches.
 if step % 200 == 0:
  print('Training loss (for one batch) at step %s: %s' % (step, float(loss_value)))
  print('Seen so far: %s samples' % ((step + 1) * 64))

到此这篇关于TensorFlow2.0使用keras训练模型的实现的文章就介绍到这了,更多相关TensorFlow2.0 keras训练模型内容请搜索三水点靠木以前的文章或继续浏览下面的相关文章希望大家以后多多支持三水点靠木!

Python 相关文章推荐
python标准日志模块logging的使用方法
Nov 01 Python
python基础教程之实现石头剪刀布游戏示例
Feb 11 Python
编程语言Python的发展史
Sep 26 Python
Python发送email的3种方法
Apr 28 Python
python提取字典key列表的方法
Jul 11 Python
Python进阶-函数默认参数(详解)
May 18 Python
[原创]教女朋友学Python(一)运行环境搭建
Nov 29 Python
Python简单生成随机数的方法示例
Mar 31 Python
python线程安全及多进程多线程实现方法详解
Sep 27 Python
详解Django3中直接添加Websockets方式
Feb 12 Python
Python非单向递归函数如何返回全部结果
Dec 18 Python
Python 机器学习工具包SKlearn的安装与使用
May 14 Python
tensorflow2.0教程之Keras快速入门
Feb 20 #Python
在Pycharm中安装Pandas库方法(简单易懂)
Feb 20 #Python
Python3爬虫RedisDump的安装步骤
Feb 20 #Python
python爬取2021猫眼票房字体加密实例
Feb 19 #Python
Python之Sklearn使用入门教程
Feb 19 #Python
Python爬虫UA伪装爬取的实例讲解
Feb 19 #Python
Pycharm制作搞怪弹窗的实现代码
Feb 19 #Python
You might like
分享PHP header函数使用教程
2013/09/05 PHP
php中apc缓存使用示例
2013/12/25 PHP
php实现将wav文件转换成图像文件并在页面中显示的方法
2015/04/21 PHP
php实现mysql数据库连接操作及用户管理
2015/11/08 PHP
解决windows上php xdebug 无法调试的问题
2020/02/19 PHP
JAVASCRIPT style 中visibility和display之间的区别
2010/01/22 Javascript
兼容IE、FireFox、Chrome等浏览器的xml处理函数js代码
2011/11/30 Javascript
javascript中call和apply方法浅谈
2013/09/27 Javascript
常用js字符串判断方法整理
2013/10/18 Javascript
引用 js在IE与FF之间的区别详细解析
2013/11/20 Javascript
如何编写高质量JS代码
2014/12/28 Javascript
js实现键盘控制DIV移动的方法
2015/01/10 Javascript
javascript实现获取字符串hash值
2015/05/10 Javascript
javascript实现网页端解压并查看zip文件
2015/12/15 Javascript
谈一谈javascript中继承的多种方式
2016/02/19 Javascript
深入解析JavaScript中函数的Currying柯里化
2016/03/19 Javascript
jquery easyui validatebox remote的使用详解
2016/11/09 Javascript
详解用node-images 打造简易图片服务器
2017/05/08 Javascript
react-native-fs实现文件下载、文本存储的示例代码
2017/09/22 Javascript
vue+express+jwt持久化登录的方法
2019/06/14 Javascript
Nodejs + Websocket 指定发送及群聊的实现
2020/01/09 NodeJs
javascript使用Blob对象实现的下载文件操作示例
2020/04/18 Javascript
[00:52]黑暗之门更新 新英雄孽主驾临DOTA2
2016/08/24 DOTA
[52:06]完美世界DOTA2联赛决赛日 Inki vs LBZS 第一场 11.08
2020/11/10 DOTA
[07:09]DOTA2-DPC中国联赛 正赛 Ehome vs Elephant 选手采访
2021/03/11 DOTA
python抓取京东商城手机列表url实例代码
2013/12/18 Python
Python简单遍历字典及删除元素的方法
2016/09/18 Python
Pytorch使用MNIST数据集实现基础GAN和DCGAN详解
2020/01/10 Python
Vita Fede官网:在意大利手工制作,在纽约市设计
2019/10/25 全球购物
澳大利亚宠物食品和用品商店:PETstock
2020/01/02 全球购物
DBA数据库管理员JAVA程序员架构师必看
2016/02/07 面试题
大一期末自我鉴定
2013/12/13 职场文书
高中生职业生涯规划书
2014/02/24 职场文书
逃课打麻将检讨书
2014/10/05 职场文书
中学生逃课检讨书
2015/02/17 职场文书
自从在 IDEA 中用了热部署神器 JRebel 之后,开发效率提升了 10(真棒)
2021/06/26 Java/Android