带有来自二进制文件的自定义训练示例的 Tensorflow 自动编码器
Tensorflow Autoencoder with custom training examples from binary file
我正在尝试调整此处找到的 Tensorflow 自动编码器代码 (https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/autoencoder.py) 以使用我自己的训练示例。我的训练示例是在二进制文件中连续保存为 UINT8 值的单通道 29*29（灰度级）图像。我创建了一个模块，它创建 data_batches 来指导培训。这是模块：
import tensorflow as tf
# various initialization variables
BATCH_SIZE = 128
N_FEATURES = 9
def batch_generator(filenames, record_bytes):
""" filenames is the list of files you want to read from.
In this case, it contains only heart.csv
"""
record_bytes = 29**2 # 29x29 images per record
filename_queue = tf.train.string_input_producer(filenames)
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes) # skip the first line in the file
_, value = reader.read(filename_queue)
print(value)
# record_defaults are the default values in case some of our columns are empty
# This is also to tell tensorflow the format of our data (the type of the decode result)
# for this dataset, out of 9 feature columns,
# 8 of them are floats (some are integers, but to make our features homogenous,
# we consider them floats), and 1 is string (at position 5)
# the last column corresponds to the lable is an integer
#record_defaults = [[1.0] for _ in range(N_FEATURES)]
#record_defaults[4] = ['']
#record_defaults.append([1])
# read in the 10 columns of data
content = tf.decode_raw(value, out_type=tf.uint8)
#print(content)
# convert the 5th column (present/absent) to the binary value 0 and 1
#condition = tf.equal(content[4], tf.constant('Present'))
#content[4] = tf.where(condition, tf.constant(1.0), tf.constant(0.0))
# pack all UINT8 values into a tensor
features = tf.stack(content)
#print(features)
# assign the last column to label
#label = content[-1]
# The bytes read represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(content, [0],
[record_bytes]),
[1, 29, 29])
# Convert from [depth, height, width] to [height, width, depth].
uint8image = tf.transpose(depth_major, [1, 2, 0])
# minimum number elements in the queue after a dequeue, used to ensure
# that the samples are sufficiently mixed
# I think 10 times the BATCH_SIZE is sufficient
min_after_dequeue = 10 * BATCH_SIZE
# the maximum number of elements in the queue
capacity = 20 * BATCH_SIZE
# shuffle the data to generate BATCH_SIZE sample pairs
data_batch = tf.train.shuffle_batch([uint8image], batch_size=BATCH_SIZE,
capacity=capacity, min_after_dequeue=min_after_dequeue)
return data_batch
然后我调整自动编码器代码以从我的输入批量馈送代码加载 batch_xs：
from __future__ import division, print_function, absolute_import
# Various initialization variables
DATA_PATH1 = 'data/building_extract_train.bin'
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
# custom imports
import data_reader
# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
# Parameters
learning_rate = 0.01
training_epochs = 20
batch_size = 256
display_step = 1
examples_to_show = 10
# Network Parameters
n_hidden_1 = 256 # 1st layer num features
n_hidden_2 = 128 # 2nd layer num features
#n_input = 784 # edge-data input (img shape: 28*28)
n_input = 841 # edge-data input (img shape: 29*29)
# tf Graph input (only pictures)
X = tf.placeholder("float", [None, n_input])
# create the data batches (queue)
# Accepts two parameters. The tensor containing the binary files and the size of a record
data_batch = data_reader.batch_generator([DATA_PATH1],29**2)
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.global_variables_initializer()
# Launch the graph
with tf.Session() as sess:
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
sess.run(init)
total_batch = int(mnist.train.num_examples/batch_size)
# Training cycle
for epoch in range(training_epochs):
# Loop over all batches
for i in range(total_batch):
#batch_xs, batch_ys = mnist.train.next_batch(batch_size)
batch_xs = sess.run([data_batch])
#print(batch_xs)
#batch_xs = tf.reshape(batch_xs, [-1, n_input])
# 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))
coord.request_stop()
coord.join(threads)
print("Optimization Finished!")
不幸的是，当 运行 代码出现此错误时：
ValueError：无法为 Tensor 'Placeholder:0' 提供形状 (1, 128, 29, 29, 1) 的值，其形状为“(?, 841)”
我的第一个问题是为什么我期望的张量是 (1, 128, 29, 29, 1)，而我期望的是 (128,29,29,1)？我在这里遗漏了什么吗？
我也不明白下面的代码，我该如何修改它以便与我的数据集进行比较：
# Applying encode and decode over test set
encode_decode = sess.run(
y_pred, feed_dict={X: mnist.test.images[:examples_to_show]})
据我了解，此代码执行图表的 y_pred 部分并将前 10 个测试图像传递给先前定义的占位符 X。如果我要为我的测试图像 (29x29) 使用第二个数据队列，我将如何将它们输入到上面的字典中？
例如，使用我的代码我可以定义一个 data_batch_eval 如下：
data_batch_eval = data_reader.batch_generator([DATA_PATH_EVAL],29**2) # eval set
尽管如此，我如何提取前 10 个测试图像以提供给字典？
My first question is why do I have Tensors of shape (1, 128, 29, 29,
1) when I was expecting (128,29,29,1)? Am I missing something here?
您需要删除 sess.run 中的括号：
batch_xs = sess.run(data_batch)
Unfortunately, when running the code I get this error: ValueError:
Cannot feed value of shape (1, 128, 29, 29, 1) for Tensor
'Placeholder:0', which has shape '(?, 841)'
您已将占位符 X 声明为 [None, 841] 并输入 [128, 29, 29, 1]:
X = tf.placeholder("float", [None, n_input])
更改您的 Feed 输入或占位符，使两者大小相同。
注意：您对队列的处理效率低下，您直接将 data_batch 作为输入传递给 network 而不是通过 feed in 机制。
我正在尝试调整此处找到的 Tensorflow 自动编码器代码 (https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/autoencoder.py) 以使用我自己的训练示例。我的训练示例是在二进制文件中连续保存为 UINT8 值的单通道 29*29（灰度级）图像。我创建了一个模块，它创建 data_batches 来指导培训。这是模块：
import tensorflow as tf
# various initialization variables
BATCH_SIZE = 128
N_FEATURES = 9
def batch_generator(filenames, record_bytes):
""" filenames is the list of files you want to read from.
In this case, it contains only heart.csv
"""
record_bytes = 29**2 # 29x29 images per record
filename_queue = tf.train.string_input_producer(filenames)
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes) # skip the first line in the file
_, value = reader.read(filename_queue)
print(value)
# record_defaults are the default values in case some of our columns are empty
# This is also to tell tensorflow the format of our data (the type of the decode result)
# for this dataset, out of 9 feature columns,
# 8 of them are floats (some are integers, but to make our features homogenous,
# we consider them floats), and 1 is string (at position 5)
# the last column corresponds to the lable is an integer
#record_defaults = [[1.0] for _ in range(N_FEATURES)]
#record_defaults[4] = ['']
#record_defaults.append([1])
# read in the 10 columns of data
content = tf.decode_raw(value, out_type=tf.uint8)
#print(content)
# convert the 5th column (present/absent) to the binary value 0 and 1
#condition = tf.equal(content[4], tf.constant('Present'))
#content[4] = tf.where(condition, tf.constant(1.0), tf.constant(0.0))
# pack all UINT8 values into a tensor
features = tf.stack(content)
#print(features)
# assign the last column to label
#label = content[-1]
# The bytes read represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(content, [0],
[record_bytes]),
[1, 29, 29])
# Convert from [depth, height, width] to [height, width, depth].
uint8image = tf.transpose(depth_major, [1, 2, 0])
# minimum number elements in the queue after a dequeue, used to ensure
# that the samples are sufficiently mixed
# I think 10 times the BATCH_SIZE is sufficient
min_after_dequeue = 10 * BATCH_SIZE
# the maximum number of elements in the queue
capacity = 20 * BATCH_SIZE
# shuffle the data to generate BATCH_SIZE sample pairs
data_batch = tf.train.shuffle_batch([uint8image], batch_size=BATCH_SIZE,
capacity=capacity, min_after_dequeue=min_after_dequeue)
return data_batch
然后我调整自动编码器代码以从我的输入批量馈送代码加载 batch_xs：
from __future__ import division, print_function, absolute_import
# Various initialization variables
DATA_PATH1 = 'data/building_extract_train.bin'
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
# custom imports
import data_reader
# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
# Parameters
learning_rate = 0.01
training_epochs = 20
batch_size = 256
display_step = 1
examples_to_show = 10
# Network Parameters
n_hidden_1 = 256 # 1st layer num features
n_hidden_2 = 128 # 2nd layer num features
#n_input = 784 # edge-data input (img shape: 28*28)
n_input = 841 # edge-data input (img shape: 29*29)
# tf Graph input (only pictures)
X = tf.placeholder("float", [None, n_input])
# create the data batches (queue)
# Accepts two parameters. The tensor containing the binary files and the size of a record
data_batch = data_reader.batch_generator([DATA_PATH1],29**2)
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.global_variables_initializer()
# Launch the graph
with tf.Session() as sess:
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
sess.run(init)
total_batch = int(mnist.train.num_examples/batch_size)
# Training cycle
for epoch in range(training_epochs):
# Loop over all batches
for i in range(total_batch):
#batch_xs, batch_ys = mnist.train.next_batch(batch_size)
batch_xs = sess.run([data_batch])
#print(batch_xs)
#batch_xs = tf.reshape(batch_xs, [-1, n_input])
# 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))
coord.request_stop()
coord.join(threads)
print("Optimization Finished!")
不幸的是，当 运行 代码出现此错误时： ValueError：无法为 Tensor 'Placeholder:0' 提供形状 (1, 128, 29, 29, 1) 的值，其形状为“(?, 841)”
我的第一个问题是为什么我期望的张量是 (1, 128, 29, 29, 1)，而我期望的是 (128,29,29,1)？我在这里遗漏了什么吗？
我也不明白下面的代码，我该如何修改它以便与我的数据集进行比较：
# Applying encode and decode over test set
encode_decode = sess.run(
y_pred, feed_dict={X: mnist.test.images[:examples_to_show]})
据我了解，此代码执行图表的 y_pred 部分并将前 10 个测试图像传递给先前定义的占位符 X。如果我要为我的测试图像 (29x29) 使用第二个数据队列，我将如何将它们输入到上面的字典中？
例如，使用我的代码我可以定义一个 data_batch_eval 如下：
data_batch_eval = data_reader.batch_generator([DATA_PATH_EVAL],29**2) # eval set
尽管如此，我如何提取前 10 个测试图像以提供给字典？
My first question is why do I have Tensors of shape (1, 128, 29, 29, 1) when I was expecting (128,29,29,1)? Am I missing something here?
您需要删除 sess.run 中的括号：
batch_xs = sess.run(data_batch)
Unfortunately, when running the code I get this error: ValueError: Cannot feed value of shape (1, 128, 29, 29, 1) for Tensor 'Placeholder:0', which has shape '(?, 841)'
您已将占位符 X 声明为 [None, 841] 并输入 [128, 29, 29, 1]:
X = tf.placeholder("float", [None, n_input])
更改您的 Feed 输入或占位符，使两者大小相同。
注意：您对队列的处理效率低下，您直接将 data_batch 作为输入传递给 network 而不是通过 feed in 机制。