AutoEncoder shape

Question

我尝试在不使用contrib的情况下在Tensorflow中创建一个自动编码器。这是的原始代码

https://github.com/Machinelearninguru/Deep_Learning/blob/master/TensorFlow/neural_networks/autoencoder/simple_autoencoder.py

这是我修改的程序：

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


ae_inputs = tf.placeholder(tf.float32, (None, 32, 32, 1))  # input to the network (MNIST images)

xi = tf.nn.conv2d(ae_inputs, 
filter=tf.Variable(tf.random_normal([5,5,1,32])), 
strides=[1,2,2,1],
padding='SAME')
print("xi {0}".format(xi))
xi = tf.nn.conv2d(xi, 
filter=tf.Variable(tf.random_normal([5,5,32,16])), 
strides=[1,2,2,32],
padding='SAME')
print("xi {0}".format(xi))
xi = tf.nn.conv2d(xi, 
filter=tf.Variable(tf.random_normal([5,5,16,8])), 
strides=[1,4,4,16],
padding='SAME')
print("xi {0}".format(xi))



xo = tf.nn.conv2d_transpose(xi, 
filter=tf.Variable(tf.random_normal([5,5,16,8])), 
output_shape=[1, 8, 8, 16],
strides=[1,4,4,1],
padding='SAME')
print("xo {0}".format(xo))
xo = tf.nn.conv2d_transpose(xo, 
filter=tf.Variable(tf.random_normal([5,5,32,16])), 
output_shape=[1, 16, 16, 32],
strides=[1,2,2,1],
padding='SAME')
print("xo {0}".format(xo))
xo = tf.nn.conv2d_transpose(xo, 
filter=tf.Variable(tf.random_normal([5,5,1,32])), 
output_shape=[1, 32, 32, 1],
strides=[1,2,2,1],
padding='SAME')
print("xo {0}".format(xo))

打印的结果是：

xi张量("Conv2D:0"，shape=(？，16，16，32(，dtype=float32(xi张量("Conv2D_1:0"，shape=(？，8，8，16(，dtype=float32(xi张量("Conv2D_2:0"，shape=(？，2，2，8(，dtype=float32(xo张量("conv2d_transpose:0"，shape=(1，8，8，16(，dtype=float32(xo张量("conv2d_transpose_1:0"，shape=(1，16，16，32(，dtype=float32(xo张量("conv2d_transpose_2:0"，shape=(1，32，32，1(，dtype=float32(

看起来输出的形状很好，但我真的不确定conv2和conv2_transpose中的所有参数。

如果需要，有人能纠正我的代码吗

编辑：@刘：我添加了relu函数，正如你告诉我的，但我不知道在哪里添加偏差：

xi = tf.nn.conv2d(ae_inputs,
filter=tf.Variable(tf.random_normal([5,5,1,32])),
strides=[1,2,2,1],
padding='SAME')
xi = tf.nn.relu(xi)
# xi = max_pool(xi,2)
print("xi {0}".format(xi))
xi = tf.nn.conv2d(xi,
filter=tf.Variable(tf.random_normal([5,5,32,16])),
strides=[1,2,2,1],
padding='SAME')
xi = tf.nn.relu(xi)
# xi = max_pool(xi,2)
print("xi {0}".format(xi))
xi = tf.nn.conv2d(xi,
filter=tf.Variable(tf.random_normal([5,5,16,8])),
strides=[1,4,4,1],
padding='SAME')
xi = tf.nn.relu(xi)
# xi = max_pool(xi,4)
print("xi {0}".format(xi))



xo = tf.nn.conv2d_transpose(xi,
filter=tf.Variable(tf.random_normal([5,5,16,8])),
output_shape=[tf.shape(xi)[0], 8, 8, 16],
strides=[1,4,4,1],
padding='SAME')
xo = tf.nn.relu(xo)
print("xo {0}".format(xo))
xo = tf.nn.conv2d_transpose(xo,
filter=tf.Variable(tf.random_normal([5,5,32,16])),
output_shape=[tf.shape(xo)[0], 16, 16, 32],
strides=[1,2,2,1],
padding='SAME')
xo = tf.nn.relu(xo)
print("xo {0}".format(xo))
xo = tf.nn.conv2d_transpose(xo,
filter=tf.Variable(tf.random_normal([5,5,1,32])),
output_shape=[tf.shape(xo)[0], 32, 32, 1],
strides=[1,2,2,1],
padding='SAME')
xo = tf.nn.tanh(xo)
print("xo {0}".format(xo))
return xo

我不明白与原始代码有什么区别：

# encoder
# 32 x 32 x 1   ->  16 x 16 x 32
# 16 x 16 x 32  ->  8 x 8 x 16
# 8 x 8 x 16    ->  2 x 2 x 8
print('inputs {0}'.format(inputs))
net = lays.conv2d(inputs, 32, [5, 5], stride=2, padding='SAME')
print('net {0}'.format(net))
net = lays.conv2d(net, 16, [5, 5], stride=2, padding='SAME')
print('net {0}'.format(net))
net = lays.conv2d(net, 8, [5, 5], stride=4, padding='SAME')
print('net {0}'.format(net))
# decoder
# 2 x 2 x 8    ->  8 x 8 x 16
# 8 x 8 x 16   ->  16 x 16 x 32
# 16 x 16 x 32  ->  32 x 32 x 1
net = lays.conv2d_transpose(net, 16, [5, 5], stride=4, padding='SAME')
print('net {0}'.format(net))
net = lays.conv2d_transpose(net, 32, [5, 5], stride=2, padding='SAME')
print('net {0}'.format(net))
net = lays.conv2d_transpose(net, 1, [5, 5], stride=2, padding='SAME', activation_fn=tf.nn.tanh)
print('net {0}'.format(net))
return net

第2版：

@刘我做了新版本的自动编码器与您的修改：

mean = 0
stdvev = 0.1
with tf.name_scope('L0'):
xi = tf.nn.conv2d(ae_inputs,
filter=tf.truncated_normal([5,5,1,32], mean = mean, stddev=stdvev),
strides=[1,1,1,1],
padding='SAME')
xi =  tf.nn.bias_add(xi, bias_variable([32]))
xi = max_pool(xi,2)
print("xi {0}".format(xi))
with tf.name_scope('L1'):
xi = tf.nn.conv2d(xi,
filter=tf.truncated_normal([5,5,32,16], mean = mean, stddev=stdvev),
strides=[1,1,1,1],
padding='SAME')
xi =  tf.nn.bias_add(xi, bias_variable([16]))
xi = max_pool(xi,2)
print("xi {0}".format(xi))
with tf.name_scope('L2'):
xi = tf.nn.conv2d(xi,
filter=tf.truncated_normal([5,5,16,8], mean = mean, stddev=stdvev),
strides=[1,1,1,1],
padding='SAME')
xi =  tf.nn.bias_add(xi, bias_variable([8]))
xi = max_pool(xi,4)
print("xi {0}".format(xi))

with tf.name_scope('L3'):
xo = tf.nn.conv2d_transpose(xi,
filter=tf.truncated_normal([5,5,16,8], mean = mean, stddev=stdvev),
output_shape=[tf.shape(xi)[0], 8, 8, 16],
strides=[1,4,4,1],
padding='SAME')
xo =  tf.nn.bias_add(xo, bias_variable([16]))
print("xo {0}".format(xo))
with tf.name_scope('L4'):
xo = tf.nn.conv2d_transpose(xo,
filter=tf.truncated_normal([5,5,32,16], mean = mean, stddev=stdvev),
output_shape=[tf.shape(xo)[0], 16, 16, 32],
strides=[1,2,2,1],
padding='SAME')
xo =  tf.nn.bias_add(xo, bias_variable([32]))
print("xo {0}".format(xo))
with tf.name_scope('L5'):
xo = tf.nn.conv2d_transpose(xo,
filter=tf.truncated_normal([5,5,1,32], mean = mean, stddev=stdvev),
output_shape=[tf.shape(xo)[0], 32, 32, 1],
strides=[1,2,2,1],
padding='SAME')
xo =  tf.nn.bias_add(xo, bias_variable([1]))
xo = tf.nn.tanh(xo)
print("xo {0}".format(xo))

但是结果是一样的，解码的值不一样。

第3版：

我从更改过滤器定义

filter=tf.truncated_normal([5,5,16,8], mean = mean, stddev=stdvev),

至

filter= tf.get_variable('filter2',[5,5,16,8]),

结果似乎收敛到更好的结果，但仍然收敛到不同的值。在原始代码(0.006(和我的版本0.015。我认为它来自于滤波器的初始值和偏差。我该怎么办？

Answer 1

您忘记了偏置和激活。所以你的网络比PCA弱。我建议您改用tf.layers。如果要使用tf.nn，请使用tf.get_variable。此外，您必须添加：tf.nn.bias_addtf.nn.relu(或任何其他激活(

如果你想知道代码是否有效，只需使用进行测试即可

sess = tf.Session()
sess.run(tf.tf.global_variables_initializer())
test_output = sess.run(xo, feed_dict={ae_inputs : np.random.random((1, 32, 32, 1))}
print(test_output)

编辑好的，所以您发布的代码基本上使用tf.layersAPI，其中包括偏差和激活。tf.nnAPI更基本，仅应用卷积，但没有激活或偏差。

根据您的编辑，我认为您希望在nn API中实现CAE。一个典型的编码器层是这样的：

conv = tf.nn.conv2d(
nput=input_tensor,
filter=tf.get_variable("conv_weight_name", shape=[height,
width,
number_input_feature_maps,
number_output_feature_maps]),
strides=[1, 1, 1, 1],
padding="SAME")
bias = tf.nn.bias_add(conv, tf.get_variable("name_bias",
[number_output_feature_maps]))
layer_out = tf.nn.relu(bias)

这里是一个典型的转置卷积层。

conv_transpose = tf.nn.conv2d_transpose(value=input_tensor,
filter=tf.get_variable("deconnv_weight_name", shape=[height,
width,
number_output_feature_maps,
number_input_feature_maps]),
output_shape=[batc_size, height_output, width_ouput, feature_maps_output],
strides=[1, 1, 1, 1])
bias = tf.nn.bias_add(conv_transpose, tf.get_variable("name_bias", shape=[number_output_feature_maps]))
layer_out = tf.nn.relu(bias)
`

如果你对这些名字有疑问，只要在通讯录里问就行了。