TensorFlow 2.0 学习笔记

一.建模流程

通常用TensorFlow实现机器学习模型，尤其常用于实现神经网络模型，但为简洁起见，一般推荐使用TensorFlow的高层次keras接口来实现神经网络模型

使用TensorFlow实现神经网络模型的一般流程为：准备数据 → 定义模型 → 训练模型 → 评估模型 → 使用模型 → 保存模型

1.准备数据

df = pd.read_csv('./data.csv')

2.定义模型 

使用keras接口有三种方式构建模型

①使用Sequential按层顺序构建模型：最简单

model = models.Sequential()
model.add(layers.Dense(20,activation = 'relu'))
...
model.summary()

②使用函数式API构建任意结构模型

inputs = layers.Input(shape=(32,32,3))
x = layers.Conv2D(32,kernel_size=(3,3))(inputs)
x = layers.MaxPool2D()(x)
...
outputs = layers.Dense(1,activation = 'sigmoid')(x)

model = models.Model(inputs = inputs,outputs = outputs)
model.summary()

③继承Model基类构建自定义模型

class CnnModel(models.Model):
  def __init__(self):
    super(CnnModel,self).__init__()

  def build(self,input_shape):
    self.embedding = layers.Embedding(MAX_WORDS，7，input_length = MAX_LEN)
    self.conv_1 = layers.Conv1D(16,kernel_size = 5,name = "conv_1",activation = "relu")
    self.pool = layers.MaxPool1D()
    self.conv_2 = layers.Conv1D(128,kernel_size = 2,name = "conv_2",activation = "relu")
    self.flatten = layers.Flatten()
    self.dense = layers.Dense(1,activation = "sigmoid")
    super(CnnModel,self).build(input_shape)

  def call(self,x):
    x = self.embedding(x)
    x = self.conv_1(x)
    x = self.pool(x)
    x = self.conv_2(x)
    x = self.pool(x)
    x = self.flatten(x)
    x = self.dense(x)
    return(x)

model = CnnModel()
model.build(input_shape = (None,MAX_LEN))
model.summary()

3.训练模型

训练模型通常有三种方法

①内置fit方法：最简单

#二分类问题选择二元交叉熵损失函数
model.compile(optimizer = 'adam',
              loss = 'binary_crossentropy',
              metrics = ['AUC'])

history = model.fit(x_train,y_train,
                    batch_size = 64,
                    epochs = 30,
                    validation_split = 0.2 #分割一部分训练数据用于验证
                    )

②内置train_on_batch方法

③自定义训练循环

4.评估模型

def plot_metric(history,metric):
  train_metrics = history.history[metric]
  val_metrics = history.history['val_' + metric]
  epochs = range(1,len(train_metrics) + 1)
  plt.plot(epochs,train_metrics,'bo--'