张量流中的基本1d卷积

Question

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 票据和手册,显然支持使用.唯一的要求就是设定strides=[1,1,1,1].听起来很简单!

但是,即使是非常小的测试用例,我也无法弄清楚如何做到这一点.我究竟做错了什么？

我们设置一下吧.

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

好的,现在在两个小阵列上生成基本卷积测试.我将通过使用1的批量大小来轻松实现,并且由于时间序列是1维的,因此我将具有1的"图像高度".并且因为它是单变量的时间序列,所以"通道"的数量显然也是1,这样会很简单吧？

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")

繁荣.错误.

ValueError: Dimensions 1 and 5 are not compatible

好的,首先,我不明白任何维度都会发生这种情况,因为我已经指定我在卷积OP中填充参数.

但很好,也许有限制.我必须弄乱文档,并在张量的错误轴上设置这个卷积.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)

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',)

嗯.好吧,现在看起来有两个问题.首先,ValueError关于沿错误的轴应用滤波器,我想,虽然有两种形式.

但是我可以应用过滤器的轴也是混乱的 - 注意它实际上构造了具有输入形状(5,1,1,1)和过滤器形状(1,1,1,3)的图形.文档中的AFAICT,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,为什么那个人工作呢？

无论如何,有时它在构造图形时不会失败.有时它会构造图形; 然后我们得到了tensorflow.python.framework.errors.InvalidArgumentError.从我收集的一些令人困惑的github门票这可能是由于事实上我是在CPU而不是GPU上运行,反之亦然事实上,卷积Op仅定义为32位浮点数,而不是64位浮点数.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.

Answer 1

我很遗憾地说,但你的第一个代码几乎是正确的.你只是倒置x和phi在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")

更新: TensorFlow现在支持自版本r0.11以来的1D卷积,使用tf.nn.conv1d.我以前做了一个指南,在我在这里粘贴的stackoverflow文档(现已灭绝)中使用它们:

一维卷积指南

考虑一个带有长度10和尺寸输入的基本示例16.批量大小是32.因此,我们有一个输入形状的占位符[batch_size, 10, 16].

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

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

最后我们应用tf.nn.conv1d一个步幅和一个填充: - 步幅:整数s - 填充:这在2D中工作,你可以选择SAME和VALID.SAME将输出相同的输入长度,而VALID不会添加零填充.

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")

输出形状应该是[batch_size, 4, 16].
有了padding="SAME",我们的输出形状会是[batch_size, 5, 16].

Answer 2

在 TF 的新版本（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)

要了解 conv1d 是如何计算的，请查看各种示例