tensorflow 2.1 用类来搭建Keras神经网络模型

一、介绍

        上一篇博客（https://mp.csdn.net/mp_blog/creation/editor/119607501）讲述了用六步法建立神经网络，但是这些神经网络层之间必须是连续的，即无法跳跃连接，因此我将介绍用类的方法来创建神经网络层。

---

二、步骤

        1. 引入库函数Model

import tensorflow as tf
from tensorflow.keras.layers import Dense
from tensorflow.keras import Model
from sklearn import datasets
import numpy as np

       2. 获取数据集并且随机打乱

x_train = datasets.load_iris().data
y_train = datasets.load_iris().target

np.random.seed(116)
np.random.shuffle(x_train)
np.random.seed(116)
np.random.shuffle(y_train)
tf.random.set_seed(116)

         3. 自定义继承Model类的子类

class IrisModel(Model):
    def __init__(self):
        super(IrisModel, self).__init__()
        self.d1 = Dense(3, activation='softmax', kernel_regularizer=tf.keras.regularizers.l2())

    def call(self, x):
        y = self.d1(x)
        return y

           注意：必须定义两个类函数：__init__( ), call ( ) 函数，init函数搭框架，call函数调用

                init函数中定义神经网络层，call中调用该层并返回.

        4. 创建对象并且构建模型

model = IrisModel()

model.compile(optimizer=tf.keras.optimizers.SGD(lr=0.1),
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

model.fit(x_train, y_train, batch_size=32, epochs=500, validation_split=0.2, validation_freq=20)
model.summary()

---

三、完整代码

import tensorflow as tf
from tensorflow.keras.layers import Dense
from tensorflow.keras import Model
from sklearn import datasets
import numpy as np

x_train = datasets.load_iris().data
y_train = datasets.load_iris().target

np.random.seed(116)
np.random.shuffle(x_train)
np.random.seed(116)
np.random.shuffle(y_train)
tf.random.set_seed(116)

class IrisModel(Model):
    def __init__(self):
        super(IrisModel, self).__init__()
        self.d1 = Dense(3, activation='softmax', kernel_regularizer=tf.keras.regularizers.l2())

    def call(self, x):
        y = self.d1(x)
        return y

model = IrisModel()

model.compile(optimizer=tf.keras.optimizers.SGD(lr=0.1),
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

model.fit(x_train, y_train, batch_size=32, epochs=500, validation_split=0.2, validation_freq=20)
model.summary()

执行结果：

参考链接：

https://www.icourse163.org/learn/PKU-1002536002?tid=1452937471#/learn/content?type=detail&id=1231331240&cid=1249443018&replay=true