自编码器
自行百度,待补充
学习
1. one_hot 独热编码
mnist = input_data.read_data_sets('MNIST_data/', one_hot = True)
可以把数据(比如5以内的数)编码成5维,数据在哪,哪个位置就是1的 [0, 0, 0, 0, 1]这种数据格式
2. 数据标准化处理
preprocessor = prep.StandardScaler().fit(X_train)
X_train = preprocessor.transform(X_train)
X_test = preprocessor.transform(X_test)
- fit
preprocessor里面存的是计算出来的训练数据的均值和方差 - transform
使用preprocessor中的均值和方差来转换数据,使数据标准化(生成0均值,标准差为1的分布)
标准化后的数据 = (原数据 - 均值 )/标准差
3. 随机数生成
np.random.randint(a,b)
生成[a,b)的随机整数,注意:左闭右开
4. MNIST数据读取
mnist = input_data.read_data_sets('MNIST_data/', one_hot = True)
# 数据格式
print(mnist.train.images.shape, mnist.train.labels.shape)
print(mnist.test.images.shape, mnist.test.labels.shape)
print(mnist.validation.images.shape, mnist.validation.labels.shape)
# 数据大小
print(mnist.train.num_examples)
print(mnist.test.num_examples)
print(mnist.validation.num_examples)
5. feed_dict 和 sess.run()
feed_dict的作用:给使用placeholder创建出来的tensor赋值,格式为字典型
cost, opt = self.sess.run((self.cost, self.optimizer), feed_dict = {self.x: X, self.scale: self.training_scale})
run(fetches, feed_dict)
喂数据feed_dict,返回fetches的值
6. 正态分布
np.random.normal(size = self.weights["b1"])
np.random.randn(size)生成标准正态分布(μ=0,σ=1),对应于np.random.normal(loc=0, scale=1, size)
numpy.random.normal(loc=0,scale=1e-2,size=shape)
- 参数loc(float):正态分布的均值,对应着这个分布的中心。loc=0说明这一个以Y轴为对称轴的正态分布,
- 参数scale(float):正态分布的标准差,对应分布的宽度,scale越大,正态分布的曲线越矮胖,scale越小,曲线越高瘦。
- 参数size(int 或者整数元组):输出的值赋在shape里,默认为None。
7. 均匀分布
tf.random_uniform((fan_in, fan_out), minval = low, maxval = high, dtype = tf.float32)
tf.random_uniform((m, n), minval, maxval, dtype)
返回m*n的矩阵,值在 [minval, maxval)范围内,数据格式为dtype的均匀分布
8. 权重初始化
代码
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):
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 AdditiveGaussianNoiseAutoencoder(object):
def __init__(self, n_input, n_hidden, transfer_function = tf.nn.softplus, optimizer = tf.train.AdamOptimizer(),
scale = 0.1):
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']))
self.reconstruction = tf.add(tf.matmul(self.hidden, self.weights['w2']), self.weights['b2'])
# cost
self.cost = 0.5 * tf.reduce_sum(tf.pow(tf.subtract(self.reconstruction, self.x), 2.0))
self.optimizer = optimizer.minimize(self.cost)
init = tf.global_variables_initializer()
self.sess = tf.Session()
self.sess.run(init)
def _initialize_weights(self):
all_weights = dict()
all_weights['w1'] = tf.Variable(xavier_init(self.n_input, self.n_hidden))
all_weights['b1'] = tf.Variable(tf.zeros([self.n_hidden], dtype = tf.float32))
all_weights['w2'] = tf.Variable(tf.zeros([self.n_hidden, self.n_input], dtype = tf.float32))
all_weights['b2'] = tf.Variable(tf.zeros([self.n_input], dtype = tf.float32))
return all_weights
def partial_fit(self, X):
cost, opt = self.sess.run((self.cost, self.optimizer), feed_dict = {self.x: X,
self.scale: self.training_scale
})
return cost
def calc_total_cost(self, X):
return self.sess.run(self.cost, feed_dict = {self.x: X,
self.scale: self.training_scale
})
def transform(self, X):
return self.sess.run(self.hidden, feed_dict = {self.x: X,
self.scale: self.training_scale
})
def generate(self, hidden = None):
if hidden is None:
hidden = np.random.normal(size = self.weights["b1"])
return self.sess.run(self.reconstruction, feed_dict = {self.hidden: hidden})
def reconstruct(self, X):
return self.sess.run(self.reconstruction, feed_dict = {self.x: X,
self.scale: self.training_scale
})
def getWeights(self):
return self.sess.run(self.weights['w1'])
def getBiases(self):
return self.sess.run(self.weights['b1'])
mnist = input_data.read_data_sets('MNIST_data', one_hot = True)
def standard_scale(X_train, X_test):
preprocessor = prep.StandardScaler().fit(X_train)
X_train = preprocessor.transform(X_train)
X_test = preprocessor.transform(X_test)
return X_train, X_test
def get_random_block_from_data(data, batch_size):
start_index = np.random.randint(0, len(data) - batch_size)
return data[start_index:(start_index + batch_size)]
X_train, X_test = standard_scale(mnist.train.images, mnist.test.images)
n_samples = int(mnist.train.num_examples)
training_epochs = 20
batch_size = 128
display_step = 1
autoencoder = AdditiveGaussianNoiseAutoencoder(n_input = 784,
n_hidden = 200,
transfer_function = tf.nn.softplus,
optimizer = tf.train.AdamOptimizer(learning_rate = 0.001),
scale = 0.01)
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(n_samples / batch_size)
# Loop over all batches
for i in range(total_batch):
batch_xs = get_random_block_from_data(X_train, batch_size)
# Fit training using batch data
cost = autoencoder.partial_fit(batch_xs)
# Compute average loss
avg_cost += cost / n_samples * batch_size
# Display logs per epoch step
if epoch % display_step == 0:
print("Epoch:", '%04d' % (epoch + 1), "cost=", "{:.9f}".format(avg_cost))
print("Total cost: " + str(autoencoder.calc_total_cost(X_test)))