tensorflow2.0学习笔记：自定义层

layers.Dense的使用方法：

1.Sequence中的使用
  layer = tf.keras.layers.Dense(100)
  layer = tf.keras.layers.Dense(100,input_shape = [None,5])
  #第一层有一个输入,None表示样本数
2. 函数式调用
  layer(tf.zeros([10,5])) #输入(10,5)，输出(10,100),
  layer.variables # x * w + b : w--kernel  b--bias
  layer.trainable_variables #获得可训练的变量：kernel,bias
  help(layer) # 查看layer的一些方法

通过继承layer类的方式实现自定义层。

import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf

from tensorflow import keras
print(tf.__version__)

2.0.0

from sklearn.datasets import fetch_california_housing
housing = fetch_california_housing()

from sklearn.model_selection import train_test_split

x_train_all, x_test, y_train_all, y_test = train_test_split(
    housing.data, housing.target, random_state = 7)
x_train, x_valid, y_train, y_valid, = train_test_split(
    x_train_all, y_train_all, random_state = 11)
print(x_train.shape, y_train.shape)
print(x_valid.shape, y_valid.shape)
print(x_test.shape, y_test.shape)

(11610, 8) (11610,)
(3870, 8) (3870,)
(5160, 8) (5160,)

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train)
x_valid_scaled = scaler.transform(x_valid)
x_test_scaked = scaler.transform(x_test)

#自定义网络层次 customized dense layer 
#通过继承类的方式实现，继承layers类

class CustomizedDenseLayer(keras.layers.Layer):
    '''初始化'''
    def __init__(self,units,activation=None,**kwargs):
        self.units = units  # 输出
        self.activation = keras.layers.Activation(activation) # 激活
        super(CustomizedDenseLayer,self).__init__(**kwargs) # 调用父类初始化函数
    
    def build(self,input_shape):
        '''构建所需要的参数，负责初始化参数'''
        # x * w + b input_shape:[None,a] -> w:[a,b] -> output_shape:[None,b]
        self.kernel = self.add_weight(name = 'kernel',
                                      shape = (input_shape[1],self.units),
                                      initializer = 'uniform',
                                      trainable = True)
        self.bias = self.add_weight(name = 'bias',
                                     shape = (self.units,),
                                     initializer = 'zeros',
                                     trainable = True)
        super(CustomizedDenseLayer,self).build(input_shape) # 调用父类build函数     
    
    def call(self,x):
        '''完成正向计算'''
        return self.activation(x @ self.kernel + self.bias)
    

#对于没有参数简单函数定义为层次时没有必要定义类，可通过Lambda定义
#tf.nn.softplus : log(1+e^x) 激活函数
customized_softplus = keras.layers.Lambda(lambda x : tf.nn.softplus(x))
print(customized_softplus([-10.,-5.,0.,5.,10.]))


model = keras.models.Sequential([
    CustomizedDenseLayer(30, activation='relu',
                         input_shape=x_train.shape[1: ]),
    CustomizedDenseLayer(1),
    customized_softplus, # 添加一个激活函数层
    #等价于 keras.layers.Dense(1,activation = 'softplus')
    #keras.layers.Dense(1),keras.layers.Activation('softplus')
])
model.summary()
model.compile(loss='mean_squared_error', optimizer="sgd",
              metrics = ["acc"])
callbacks = [keras.callbacks.EarlyStopping(
    patience=5, min_delta=1e-2)]

tf.Tensor([4.5417706e-05 6.7153489e-03 6.9314718e-01 5.0067153e+00 1.0000046e+01], shape=(5,), dtype=float32)
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
customized_dense_layer (Cust (None, 30)                270       
_________________________________________________________________
customized_dense_layer_1 (Cu (None, 1)                 31        
_________________________________________________________________
lambda_1 (Lambda)            (None, 1)                 0         
=================================================================
Total params: 301
Trainable params: 301
Non-trainable params: 0
_________________________________________________________________

history = model.fit(x_train_scaled, y_train,
                   validation_data = (x_valid_scaled, y_valid),
                   epochs = 100,
                   callbacks = callbacks)