tensorflow框架（二）网络搭建八股和鸢尾花分类

六步法（sequential方法）

import

train, test

model = tf.keras.models.Sequential

搭建网络

model.compile

告知训练方法

model.fit

model.summary（）

打印出网络结构和参数统计

鸢尾花分类

import tensorflow as tf
from sklearn import datasets
import numpy as np

x_train = datasets.load_iris().data #测试集在后面model.fit中用validation_spilt划分
y_train = datasets.load_iris().target

#实现数据集的乱序
np.random.seed(116)
np.random.shuffle(x_train)
np.random.seed(116)
np.random.shuffle(y_train)
tf.random.set_seed(116)

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()

六步法（用类class）

import

train, test

class MyModel(Model) model = MyModel

class MyModel(Model):
	def _init_(self):
		super(Mymodel, self)._init_()
		定义网络结构块 # 给出搭建神经网络所需的结构块
	def call(self, x):
		调用网络结构块，实现前向传播
		return y
model = MyModel()	

model.compile

model.fit

model.summary

用类实现鸢尾花分类

import tensorflow as tf
from tensorflow.keras.layers import Dense #新增
from tensorflow.keras import Model # 新增
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)

#新增
class IrisModel(Model):
    def __init__(self):
        super(IrisModel, self).__init__()
        self.d1 = Dense(3, activation='softmax', kernel_regularizer=tf.keras.regularizers.l2()) #具有三个神经元的全连接网络
        
    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()