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: