1. 模型简介
为了提高自编码器的泛化性能和鲁棒性,在输入的数据中,我们加入高斯白噪声,通过深度网络进行学习,以获取“无噪声”情况下的输出数据——有一点向去除噪声,实际上,最开始通过堆叠的自动编码器实现噪声去除。
2. 模型实现
(注意:模型和AE的区别就是,输入网络的数据是加噪声的数据,代价函数却采用的是无噪声数据进行计算)
# whilt gaussian noise Auto-Encoder # # Author: HSW # Date: 2018-05-07 # import tensorflow as tf import numpy as np def axvier_init(fan_in, fan_out, constant = 1): ''' Initial weights ''' 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) class NoiseAutoEncoder(object): def __init__(self, AutoEncoder_Shape = (128, 256, 128), transfer_function = tf.nn.softplus, optimizer = tf.train.AdamOptimizer(), sigma = 0.1): ''' Constructor Funcion ''' self.sigma = sigma self.LayerCnt = len(AutoEncoder_Shape) self.AutoEncoder_Shape = AutoEncoder_Shape self.transfer = transfer_function self.weights = self.init_weights() self.layers = self.init_layers() self.total_loss = self.init_loss() self.optimizer = optimizer.minimize(self.total_loss) init = tf.global_variables_initializer() self.sess = tf.Session() self.sess.run(init) def init_weights(self): ''' AutoEncoder Weights ''' all_weights = dict() for iter in range(self.LayerCnt - 1): weightName = "weight" + str(iter + 1) biasName = "bias" + str(iter + 1) if iter == self.LayerCnt - 2: all_weights[weightName] = tf.Variable(axvier_init(self.AutoEncoder_Shape[iter], self.AutoEncoder_Shape[iter + 1])) all_weights[biasName] = tf.Variable(tf.zeros([self.AutoEncoder_Shape[iter + 1]])) else: all_weights[weightName] = tf.Variable(tf.zeros([self.AutoEncoder_Shape[iter], self.AutoEncoder_Shape[iter + 1]])) all_weights[biasName] = tf.Variable(tf.zeros([self.AutoEncoder_Shape[iter + 1]])) return all_weights def init_layers(self): ''' AutoEncoder: Input Layer + Hidden Layer + Output Layer ''' all_layers = dict() all_layers['inputs'] = tf.placeholder(tf.float32, [None, self.AutoEncoder_Shape[0]]) # gaussian noise layers all_layers['noise_inputs'] = all_layers['inputs'] + self.sigma * tf.random_normal((self.AutoEncoder_Shape[0], ), mean = 0, stddev=1.0, dtype=tf.float32) for iter in range(self.LayerCnt - 1): if iter == 0: # inputs noise Layer => 1th Hidden Layer preLayerName = 'noise_inputs' layerName = 'hidden' + str(iter + 1) weightName = 'weight' + str(iter + 1) biasName = 'bias' + str(iter + 1) all_layers[layerName] = self.transfer(tf.add(tf.matmul(all_layers[preLayerName], self.weights[weightName]), self.weights[biasName])) elif iter == self.LayerCnt - 2: # Last Hidden Layer => outputs Layer preLayerName = 'hidden' + str(iter) layerName = 'outputs' weightName = 'weight' + str(iter + 1) biasName = 'bias' + str(iter + 1) all_layers[layerName] = tf.add(tf.matmul(all_layers[preLayerName], self.weights[weightName]), self.weights[biasName]) else: # pre-Hidden Layer => cur-Hidden Layer preLayerName = 'hidden' + str(iter) layerName = 'hidden' + str(iter + 1) weightNmae = 'weight' + str(iter + 1) biasName = 'bias' + str(iter + 1) all_layers[layerName] = self.transfer(tf.add(tf.matmul(all_layers[preLayerName], self.weights[weightName]), self.weights[biasName])) return all_layers def init_loss(self): ''' AutoEncoder Loss ''' return 0.5 * tf.reduce_sum(tf.pow(tf.subtract(self.layers['outputs'], self.layers['inputs']), 2)) def partial_fit(self, inputs): ''' For train ''' cost, opt = self.sess.run((self.total_loss, self.optimizer), feed_dict={self.layers['inputs']: inputs}) return cost def calc_total_cost(self, inputs): ''' For evalution ''' return self.sess.run(self.total_loss, feed_dict={self.inputs: inputs}) def transform(self, inputs, layerNum): ''' inputs => Encode Feature ''' hiddenName = 'hidden' + str(layerNum) return self.sess.run(self.layers[hiddenName], feed_dict={self.layers['inputs']: inputs}) def generate(self, hidden = None, layerNum = 1): ''' Encode Feature => outputs ''' hiddenName = 'hidden' + str(layerNum) return self.sess.run(self.layers['outputs'], feed_dict={self.layers[hiddenName]: hidden}) def reconstruct(self, inputs): ''' inputs => outputs ''' return self.sess.run(self.layers['outputs'], feed_dict={self.layers['inputs']: inputs}) def getWeigths(self, layerNum): ''' weight of layerNum-th layer ''' weightName = 'weight' + str(layerNum) return self.sess.run(self.weights[weightName]) def getBiases(self, layerNum): ''' bias of layerNum-th layer ''' biasName = 'bias' + str(layerNum) return self.sess.run(self.weights[biasName]) if __name__ == "__main__": noiseAutoEncoder = NoiseAutoEncoder(); print(noiseAutoEncoder.layers) print(noiseAutoEncoder.weights['weight1']) print(noiseAutoEncoder.weights['bias1']) print(autoEncoder.weights['weight2']) print(autoEncoder.weights['bias2'])
3. 模型测试