python - Tensorflow 自动编码器成本不会降低？

Question

我正在使用 Tensorflow 使用自动编码器进行无监督特征学习。我为 Amazon csv 数据集编写了以下代码，当我运行它时，每次迭代的成本都不会降低。你能帮我找到代码中的错误吗？

from __future__ import division, print_function, absolute_import

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
df=pd.read_csv('../dataset/amazon_1_b.csv')
df=df.drop(df.columns[0], axis=1)
#df1, df2 = df[:25000, :], df[25000:, :] if len(df) > 25000 else df, None
df1=df.head(25000)
df2=df.tail(len(df)-25000)
trY=df1['ACTION'].as_matrix()
teY=df2['ACTION'].as_matrix()
df1=df1.drop(df.columns[9], axis=1)
df2=df2.drop(df.columns[9], axis=1)
trX=df1.as_matrix()
teX=df2.as_matrix()



# Parameters
learning_rate = 0.01
training_epochs = 50
batch_size = 20
display_step = 1
examples_to_show = 10

# Network Parameters
n_hidden_1 = 20 # 1st layer num features
n_hidden_2 = 5 # 2nd layer num features
n_input = trX.shape[1] # MNIST data input (img shape: 28*28)

# tf Graph input (only pictures)
X = tf.placeholder("float", [None, n_input])

weights = {
    'encoder_h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
    'encoder_h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
    'decoder_h1': tf.Variable(tf.random_normal([n_hidden_2, n_hidden_1])),
    'decoder_h2': tf.Variable(tf.random_normal([n_hidden_1, n_input])),
}
biases = {
    'encoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'encoder_b2': tf.Variable(tf.random_normal([n_hidden_2])),
    'decoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'decoder_b2': tf.Variable(tf.random_normal([n_input])),
}



# Building the encoder
def encoder(x):
    # Encoder Hidden layer with sigmoid activation #1
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['encoder_h1']),
                                   biases['encoder_b1']))
    # Decoder Hidden layer with sigmoid activation #2
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['encoder_h2']),
                                   biases['encoder_b2']))
    return layer_2


# Building the decoder
def decoder(x):
    # Encoder Hidden layer with sigmoid activation #1
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['decoder_h1']),
                                   biases['decoder_b1']))
    # Decoder Hidden layer with sigmoid activation #2
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['decoder_h2']),
                                   biases['decoder_b2']))
    return layer_2

# Construct model
encoder_op = encoder(X)
decoder_op = decoder(encoder_op)

# Prediction
y_pred = decoder_op
# Targets (Labels) are the input data.
y_true = X

# Define loss and optimizer, minimize the squared error
cost = tf.reduce_mean(tf.pow(y_true - y_pred, 2))
optimizer = tf.train.RMSPropOptimizer(learning_rate).minimize(cost)

# Initializing the variables
init = tf.initialize_all_variables()



# Launch the graph
# Using InteractiveSession (more convenient while using Notebooks)
sess = tf.InteractiveSession()
sess.run(init)

total_batch = int(trX.shape[0]/batch_size)
# Training cycle
for epoch in range(training_epochs):
    # Loop over all batches
    for i in range(total_batch):
        batch_xs= trX[batch_size*i:batch_size*(i+1)]
        # Run optimization op (backprop) and cost op (to get loss value)
        _, c = sess.run([optimizer, cost], feed_dict={X: batch_xs})
    # Display logs per epoch step
    if epoch % display_step == 0:
        print("Epoch:", '%04d' % (epoch+1),
              "cost=", "{:.9f}".format(c))

print("Optimization Finished!")

# Applying encode and decode over test set
encode_decode = sess.run(
    y_pred, feed_dict={X: teX})

数据集的链接是here .python 文件的链接是 here .

以下是直到第 31 个纪元的结果，直到所有 50 个纪元都保持不变。

Epoch: 0001 cost= 18134403072.000000000
Epoch: 0002 cost= 18134403072.000000000
Epoch: 0003 cost= 18134403072.000000000
Epoch: 0004 cost= 18134403072.000000000
Epoch: 0005 cost= 18134403072.000000000
Epoch: 0006 cost= 18134403072.000000000
Epoch: 0007 cost= 18134403072.000000000
Epoch: 0008 cost= 18134403072.000000000
Epoch: 0009 cost= 18134403072.000000000
Epoch: 0010 cost= 18134403072.000000000
Epoch: 0011 cost= 18134403072.000000000
Epoch: 0012 cost= 18134403072.000000000
Epoch: 0013 cost= 18134403072.000000000
Epoch: 0014 cost= 18134403072.000000000
Epoch: 0015 cost= 18134403072.000000000
Epoch: 0016 cost= 18134403072.000000000
Epoch: 0017 cost= 18134403072.000000000
Epoch: 0018 cost= 18134403072.000000000
Epoch: 0019 cost= 18134403072.000000000
Epoch: 0020 cost= 18134403072.000000000
Epoch: 0021 cost= 18134403072.000000000
Epoch: 0022 cost= 18134403072.000000000
Epoch: 0023 cost= 18134403072.000000000
Epoch: 0024 cost= 18134403072.000000000
Epoch: 0025 cost= 18134403072.000000000
Epoch: 0026 cost= 18134403072.000000000
Epoch: 0027 cost= 18134403072.000000000
Epoch: 0028 cost= 18134403072.000000000
Epoch: 0029 cost= 18134403072.000000000
Epoch: 0030 cost= 18134403072.000000000
Epoch: 0031 cost= 18134403072.000000000

Answer 1

在这种情况下，您的优化方法 RMSPropOptimizer 似乎真的很慢。

您可能想尝试亚当斯的解决方案，至少对我有用。