Python 张量流中的基本一维卷积

Basic 1d convolution in tensorflow

提问by dan mackinlay

OK, I'd like to do a 1-dimensional convolution of time series data in Tensorflow. This is apparently supported using tf.nn.conv2d, according to thesetickets, and the manual. the only requirement is to set strides=[1,1,1,1]. Sounds simple!

好的，我想在 Tensorflow 中对时间序列数据进行一维卷积。tf.nn.conv2d根据这些票证和手册，这显然是支持使用的。唯一的要求是设置strides=[1,1,1,1]. 听起来很简单！

However, I cannot work out how to do this in even a very minimal test case. What am I doing wrong?

但是，即使在一个非常小的测试用例中，我也无法弄清楚如何做到这一点。我究竟做错了什么？

Let's set this up.

让我们设置一下。

import tensorflow as tf
import numpy as np
print(tf.__version__)
>>> 0.9.0

OK, now generate a basic convolution test on two small arrays. I will make it easy by using a batch size of 1, and since time series are 1-dimensional, I will have an "image height" of 1. And since it's a univariate time series, clearly the number of "channels" is also 1, so this will be simple, right?

好的，现在在两个小数组上生成一个基本的卷积测试。我将通过使用 1 的批量大小来简化它，并且由于时间序列是一维的，因此我的“图像高度”为 1。而且由于它是单变量时间序列，显然“通道”的数量也是1，所以这会很简单，对吧？

g = tf.Graph()
with g.as_default():
    # data shape is "[batch, in_height, in_width, in_channels]",
    x = tf.Variable(np.array([0.0, 0.0, 0.0, 0.0, 1.0]).reshape(1,1,-1,1), name="x")
    # filter shape is "[filter_height, filter_width, in_channels, out_channels]"
    phi = tf.Variable(np.array([0.0, 0.5, 1.0]).reshape(1,-1,1,1), name="phi")
    conv = tf.nn.conv2d(
        phi,
        x,
        strides=[1, 1, 1, 1],
        padding="SAME",
        name="conv")

BOOM. Error.

繁荣。错误。

ValueError: Dimensions 1 and 5 are not compatible

OK, For a start, I don't understand how this should happen with anydimension, since I've specified that I'm padding the arguments in the convolution OP.

好的，首先，我不明白这应该如何在任何维度上发生，因为我已经指定我正在填充卷积 OP 中的参数。

but fine, maybe there are limits to that. I must have got the documentation confused and set up this convolution on the wrong axes of the tensor. I'll try all possible permutations:

但是很好，也许这有限制。我一定把文档弄糊涂了，并在张量的错误轴上设置了这个卷积。我会尝试所有可能的排列：

for i in range(4):
    for j in range(4):
        shape1 = [1,1,1,1]
        shape1[i] = -1
        shape2 = [1,1,1,1]
        shape2[j] = -1
        x_array = np.array([0.0, 0.0, 0.0, 0.0, 1.0]).reshape(*shape1)
        phi_array = np.array([0.0, 0.5, 1.0]).reshape(*shape2)
        try:
            g = tf.Graph()
            with g.as_default():
                x = tf.Variable(x_array, name="x")
                phi = tf.Variable(phi_array, name="phi")
                conv = tf.nn.conv2d(
                    x,
                    phi,
                    strides=[1, 1, 1, 1],
                    padding="SAME",
                    name="conv")
                init_op = tf.initialize_all_variables()
            sess = tf.Session(graph=g)
            sess.run(init_op)
            print("SUCCEEDED!", x_array.shape, phi_array.shape, conv.eval(session=sess))
            sess.close()
        except Exception as e:
            print("FAILED!", x_array.shape, phi_array.shape, type(e), e.args or e._message)

Result:

结果：

FAILED! (5, 1, 1, 1) (3, 1, 1, 1) <class 'ValueError'> ('Filter must not be larger than the input: Filter: (3, 1) Input: (1, 1)',)
FAILED! (5, 1, 1, 1) (1, 3, 1, 1) <class 'ValueError'> ('Filter must not be larger than the input: Filter: (1, 3) Input: (1, 1)',)
FAILED! (5, 1, 1, 1) (1, 1, 3, 1) <class 'ValueError'> ('Dimensions 1 and 3 are not compatible',)
FAILED! (5, 1, 1, 1) (1, 1, 1, 3) <class 'tensorflow.python.framework.errors.InvalidArgumentError'> No OpKernel was registered to support Op 'Conv2D' with these attrs
     [[Node: conv = Conv2D[T=DT_DOUBLE, data_format="NHWC", padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true](x/read, phi/read)]]
FAILED! (1, 5, 1, 1) (3, 1, 1, 1) <class 'tensorflow.python.framework.errors.InvalidArgumentError'> No OpKernel was registered to support Op 'Conv2D' with these attrs
     [[Node: conv = Conv2D[T=DT_DOUBLE, data_format="NHWC", padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true](x/read, phi/read)]]
FAILED! (1, 5, 1, 1) (1, 3, 1, 1) <class 'ValueError'> ('Filter must not be larger than the input: Filter: (1, 3) Input: (5, 1)',)
FAILED! (1, 5, 1, 1) (1, 1, 3, 1) <class 'ValueError'> ('Dimensions 1 and 3 are not compatible',)
FAILED! (1, 5, 1, 1) (1, 1, 1, 3) <class 'tensorflow.python.framework.errors.InvalidArgumentError'> No OpKernel was registered to support Op 'Conv2D' with these attrs
     [[Node: conv = Conv2D[T=DT_DOUBLE, data_format="NHWC", padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true](x/read, phi/read)]]
FAILED! (1, 1, 5, 1) (3, 1, 1, 1) <class 'ValueError'> ('Filter must not be larger than the input: Filter: (3, 1) Input: (1, 5)',)
FAILED! (1, 1, 5, 1) (1, 3, 1, 1) <class 'tensorflow.python.framework.errors.InvalidArgumentError'> No OpKernel was registered to support Op 'Conv2D' with these attrs
     [[Node: conv = Conv2D[T=DT_DOUBLE, data_format="NHWC", padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true](x/read, phi/read)]]
FAILED! (1, 1, 5, 1) (1, 1, 3, 1) <class 'ValueError'> ('Dimensions 1 and 3 are not compatible',)
FAILED! (1, 1, 5, 1) (1, 1, 1, 3) <class 'tensorflow.python.framework.errors.InvalidArgumentError'> No OpKernel was registered to support Op 'Conv2D' with these attrs
     [[Node: conv = Conv2D[T=DT_DOUBLE, data_format="NHWC", padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true](x/read, phi/read)]]
FAILED! (1, 1, 1, 5) (3, 1, 1, 1) <class 'ValueError'> ('Dimensions 5 and 1 are not compatible',)
FAILED! (1, 1, 1, 5) (1, 3, 1, 1) <class 'ValueError'> ('Dimensions 5 and 1 are not compatible',)
FAILED! (1, 1, 1, 5) (1, 1, 3, 1) <class 'ValueError'> ('Dimensions 5 and 3 are not compatible',)
FAILED! (1, 1, 1, 5) (1, 1, 1, 3) <class 'ValueError'> ('Dimensions 5 and 1 are not compatible',)

Hmm. OK, it looks like there are two problems now. Firstly, the ValueErroris about applying the filter along the wrong axis, I guess, although there are two forms.

唔。好的，现在看起来有两个问题。首先，ValueError我猜是关于沿错误的轴应用过滤器，尽管有两种形式。

But then the axes along which I can apply the filter are confusing too - notice that it actually constructs the graph with input shape (5, 1, 1, 1) and filter shape (1, 1, 1, 3). AFAICT from the documentation, this should be a filter that looks at on example from the batch, one "pixel" and one "channel" and outputs 3 "channels". Why does that one work, then, when others do not?

但是随后我可以应用过滤器的轴也令人困惑 - 请注意，它实际上构建了具有输入形状 (5, 1, 1, 1) 和过滤器形状 (1, 1, 1, 3) 的图形。AFAICT 从文档中可以看出，这应该是一个过滤器，它从批处理中查看示例，一个“像素”和一个“通道”并输出 3 个“通道”。那么，当其他方法不起作用时，为什么该方法有效？

Anyway, sometimes it does not fail while constructing the graph. Sometime it constructs the graph; then we get the tensorflow.python.framework.errors.InvalidArgumentError. From some confusing github ticketsI gather this is probably due to the fact that I'm running on CPU instead of GPU, or vice versathe fact that the convolution Op is only defined for 32 bit floats, not 64 bit floats. If anyone could throw some light on whichaxes I should be aligning whaton, in order to convolve a time series with a kernel, I'd be very grateful.

无论如何，有时在构建图形时它不会失败。有时它构建图形；然后我们得到tensorflow.python.framework.errors.InvalidArgumentError. 从一些令人困惑的 github 票证中，我认为这可能是由于我在 CPU 而不是 GPU 上运行的事实，反之亦然卷积 Op 仅针对 32 位浮点数而不是 64 位浮点数定义的事实。如果任何人都可能会引发一些光其轴我应该对准什么上，为了与卷积内核时间序列，我会非常感激。

回答by Olivier Moindrot

I am sorry to say that, but your first code was almost right. You just inverted xand phiin tf.nn.conv2d:

我很抱歉这么说，但你的第一个代码几乎是正确的。您刚刚倒置x并phi进入tf.nn.conv2d：

g = tf.Graph()
with g.as_default():
    # data shape is "[batch, in_height, in_width, in_channels]",
    x = tf.Variable(np.array([0.0, 0.0, 0.0, 0.0, 1.0]).reshape(1, 1, 5, 1), name="x")
    # filter shape is "[filter_height, filter_width, in_channels, out_channels]"
    phi = tf.Variable(np.array([0.0, 0.5, 1.0]).reshape(1, 3, 1, 1), name="phi")
    conv = tf.nn.conv2d(
        x,
        phi,
        strides=[1, 1, 1, 1],
        padding="SAME",
        name="conv")

---

---

Update:TensorFlow now supports 1D convolution since version r0.11, using tf.nn.conv1d. I previously made a guide to use them in the stackoverflow documentation (now extinct) that I'm pasting here:

更新：TensorFlow 从 r0.11 版本开始支持一维卷积，使用tf.nn.conv1d. 我之前在我粘贴在这里的 stackoverflow 文档（现已灭绝）中制作了一个使用它们的指南：

---

---

Guide to 1D convolution

一维卷积指南

Consider a basic example with an input of length 10, and dimension 16. The batch size is 32. We therefore have a placeholder with input shape [batch_size, 10, 16].

考虑一个输入长度10和维度的基本示例16。批量大小为32. 因此，我们有一个带有输入形状的占位符[batch_size, 10, 16]。

batch_size = 32
x = tf.placeholder(tf.float32, [batch_size, 10, 16])

We then create a filter with width 3, and we take 16channels as input, and output also 16channels.

然后我们创建一个宽度为 3 的过滤器，我们将16通道作为输入，并输出16通道。

filter = tf.zeros([3, 16, 16])  # these should be real values, not 0

---

---

Finally we apply tf.nn.conv1dwith a stride and a padding: - stride: integer s- padding: this works like in 2D, you can choose between SAMEand VALID. SAMEwill output the same input length, while VALIDwill not add zero padding.

最后，我们应用tf.nn.conv1dstride 和 padding： - stride: integer s- padding：这就像在 2D 中一样，您可以在SAME和之间进行选择VALID。SAME将输出相同的输入长度，同时VALID不会添加零填充。

For our example we take a stride of 2, and a valid padding.

对于我们的示例，我们采用 2 的步幅和有效的填充。

output = tf.nn.conv1d(x, filter, stride=2, padding="VALID")

The output shape should be [batch_size, 4, 16].
With padding="SAME", we would have had an output shape of [batch_size, 5, 16].

输出形状应该是[batch_size, 4, 16].
使用padding="SAME"，我们的输出形状为[batch_size, 5, 16]。

回答by Salvador Dali

In the new versions of TF (starting from 0.11) you have conv1d, so there is no need to use 2d convolution to do 1d convolution. Here is a simple example of how to use conv1d:

在新版本的 TF（从 0.11 开始）中，您有conv1d，因此无需使用 2d 卷积来进行 1d 卷积。这是一个如何使用 conv1d 的简单示例：

import tensorflow as tf
i = tf.constant([1, 0, 2, 3, 0, 1, 1], dtype=tf.float32, name='i')
k = tf.constant([2, 1, 3], dtype=tf.float32, name='k')

data   = tf.reshape(i, [1, int(i.shape[0]), 1], name='data')
kernel = tf.reshape(k, [int(k.shape[0]), 1, 1], name='kernel')

res = tf.squeeze(tf.nn.conv1d(data, kernel, stride=1, padding='VALID'))
with tf.Session() as sess:
    print sess.run(res)

To understand how conv1d is calculates, take a look at various examples

要了解 conv1d 是如何计算的，请查看各种示例

回答by Pinocchio

I think I got it to work with the requirements that I needed. The comments/details of how it works are on the code:

我想我让它能够满足我需要的要求。它如何工作的注释/细节在代码上：

import numpy as np

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

task_name = 'task_MNIST_flat_auto_encoder'
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
X_train, Y_train = mnist.train.images, mnist.train.labels # N x D
X_cv, Y_cv = mnist.validation.images, mnist.validation.labels
X_test, Y_test = mnist.test.images, mnist.test.labels

# data shape is "[batch, in_height, in_width, in_channels]",
# X_train = N x D
N, D = X_train.shape
# think of it as N images with height 1 and width D.
X_train = X_train.reshape(N,1,D,1)
x = tf.placeholder(tf.float32, shape=[None,1,D,1], name='x-input')
#x = tf.Variable( X_train , name='x-input')
# filter shape is "[filter_height, filter_width, in_channels, out_channels]"
filter_size, nb_filters = 10, 12 # filter_size , number of hidden units/units
# think of it as having nb_filters number of filters, each of size filter_size
W = tf.Variable( tf.truncated_normal(shape=[1, filter_size, 1,nb_filters], stddev=0.1) )
stride_convd1 = 2 # controls the stride for 1D convolution
conv = tf.nn.conv2d(input=x, filter=W, strides=[1, 1, stride_convd1, 1], padding="SAME", name="conv")

with tf.Session() as sess:
    sess.run( tf.initialize_all_variables() )
    sess.run(fetches=conv, feed_dict={x:X_train})

thanks to Olivier for the help (see the discussion in his comments for further clarification).

感谢 Olivier 的帮助（请参阅他评论中的讨论以进一步澄清）。

---

---

Manually check it:

手动检查：

X_train_org = np.array([[0,1,2,3]])
N, D = X_train_org.shape
X_train_1d = X_train_org.reshape(N,1,D,1)
#X_train = tf.constant( X_train_org )
# think of it as N images with height 1 and width D.
xx = tf.placeholder(tf.float32, shape=[None,1,D,1], name='xx-input')
#x = tf.Variable( X_train , name='x-input')
# filter shape is "[filter_height, filter_width, in_channels, out_channels]"
filter_size, nb_filters = 2, 2 # filter_size , number of hidden units/units
# think of it as having nb_filters number of filters, each of size filter_size
filter_w = np.array([[1,3],[2,4]]).reshape(1,filter_size,1,nb_filters)
#W = tf.Variable( tf.truncated_normal(shape=[1,filter_size,1,nb_filters], stddev=0.1) )
W = tf.Variable( tf.constant(filter_w, dtype=tf.float32) )
stride_convd1 = 2 # controls the stride for 1D convolution
conv = tf.nn.conv2d(input=xx, filter=W, strides=[1, 1, stride_convd1, 1], padding="SAME", name="conv")

#C = tf.constant( (np.array([[4,3,2,1]]).T).reshape(1,1,1,4) , dtype=tf.float32 ) #
#tf.reshape( conv , [])
#y_tf = tf.matmul(conv, C)


##
x = tf.placeholder(tf.float32, shape=[None,D], name='x-input') # N x 4
W1 = tf.Variable( tf.constant( np.array([[1,2,0,0],[3,4,0,0]]).T, dtype=tf.float32 ) ) # 2 x 4
y1 = tf.matmul(x,W1) # N x 2 = N x 4 x 4 x 2
W2 = tf.Variable( tf.constant( np.array([[0,0,1,2],[0,0,3,4]]).T, dtype=tf.float32 ))
y2 = tf.matmul(x,W2) # N x 2 = N x 4 x 4 x 2
C1 = tf.constant( np.array([[4,3]]).T, dtype=tf.float32 ) # 1 x 2
C2 = tf.constant( np.array([[2,1]]).T, dtype=tf.float32 )

p1 = tf.matmul(y1,C1)
p2 = tf.matmul(y2,C2)
y = p1 + p2
with tf.Session() as sess:
    sess.run( tf.initialize_all_variables() )
    print 'manual conv'
    print sess.run(fetches=y1, feed_dict={x:X_train_org})
    print sess.run(fetches=y2, feed_dict={x:X_train_org})
    #print sess.run(fetches=y, feed_dict={x:X_train_org})
    print 'tf conv'
    print sess.run(fetches=conv, feed_dict={xx:X_train_1d})
    #print sess.run(fetches=y_tf, feed_dict={xx:X_train_1d})

outputs:

输出：

manual conv
[[ 2.  4.]]
[[  8.  18.]]
tf conv
[[[[  2.   4.]
   [  8.  18.]]]]