【tensorflow】加性高斯噪声AutoEncoder_10db高斯噪声tensorflow-优快云博客

本文介绍了如何利用TensorFlow实战中的方法，构建一个加性高斯噪声AutoEncoder模型。通过引入高斯噪声，该模型能增强对输入数据的鲁棒性。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

#coding=utf8
import numpy as np
import sklearn.preprocessing as prep
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

def xavier_init(fan_in, fan_out, constant = 1): # 泽威尔初始化
    low = -constant * np.sqrt(6.0 / (fan_in + fan_out))
    high = constant * np.sqrt(6.0 / (fan_in + fan_out))
    return tf.random_uniform((fan_in, fan_out),minval = low, maxval = high,dtype = tf.float32) # 均值为0,方差为2/(n_in + n_out)的均匀分布

class AdditiveGaussianNoiseAutoencoder(object): # 加性高斯噪声自编码器
    def __init__(self, n_input, n_hidden, transfer_function = tf.nn.softplus, optimizer = tf.train.AdamOptimizer(),
                 scale = 0.1):
        '''
        n_input: 输入变量数
        n_hidden: 隐含层节点数
        transfer_function: 隐含层激活函数
        optimizer: 优化器
        scale: 高斯噪声系数
        '''
        self.n_input = n_input
        self.n_hidden = n_hidden
        self.transfer = transfer_function
        self.scale = tf.placeholder(tf.float32)
        self.training_scale = scale
        network_weights = self._initialize_weights()
        self.weights = network_weights

        # model
        self.x = tf.placeholder(tf.float32, [None, self.n_input])
        self.hidden = self.transfer(tf.add(tf.matmul(self.x + scale * tf.random_normal((n_input,)),
                self.weights['w1']),
                self.weights['b1']))
        # (x + s * n) * w1 + b1 ，噪声n是 tf.random_normal((n_input,))，如果写出 tf.random_norma