用tensorflow.keras模块化搭建神经网络模型

资料来源：北京大学 曹建教授的课程 人工智能实践：TensorFlow笔记

使用八股搭建神经网络

其中第三步使用Sequential只能搭建简易的全连接模型，如果是有跳转的卷积网络或者其他复杂设计的网络需要自己创建一个类来设计；



利用鸢尾花数据集来搭建网络举例：

# 用sequential或自己搭建model类
import tensorflow as tf
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)
# ******************
# 可以自己搭建模型类，效果一样
# 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 = tf.keras.models.Sequential([
    tf.keras.layers.Dense(3, activation='softmax', kernel_regularizer=tf.keras.regularizers.l2())
])

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()

使用mnist数据集搭建神经网络

import tensorflow as tf
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras import Model

mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

class MnistModel(Model):
    def __init__(self):
        super(MnistModel, self).__init__()
        self.flatten = Flatten()
        self.d1 = Dense(128, activation='relu')
        self.d2 = Dense(10, activation='softmax')

    def call(self, x):
        x = self.flatten(x)
        x = self.d1(x)
        y = self.d2(x)
        return y

model = MnistModel()

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

model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()