7

I am working on unsupervised feature learning using autoencoders using Tensorflow. I have written following code for the Amazon csv dataset and when I am running it the cost is not decreasing at every iteration. Can you please help me find the bug in the code. 

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})

The link to the dataset is here. The link to the python file is here.

Following is the result untill 31 epoch and it remains same till all 50 epoch.

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
4

1 回答 1

0

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。

于 2016-12-04T08:20:05.047 回答