Use tensorflow.keras to build a neural network model modularly

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

The third step to useSequentialThe full connection model building temporary must,If there is a jump is the convolution of the network or other complicated design of network need to create a class to design;



Iris data set is used to set up network for example：

# 用sequentialOr buildmodel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)
# ******************
# Can set up a model class,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mnistData set to build neural network

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()