TensorFlow:numpy.repeat() 替代方案 [英] TensorFlow: numpy.repeat() alternative

问题描述

我想以成对的方式比较来自我的神经网络的预测值 yp，所以我使用了(回到我旧的 numpy 实现中):

I want to compare the predicted values yp from my neural network in a pairwise fashion, and so I was using (back in my old numpy implementation):

idx = np.repeat(np.arange(len(yp)), len(yp))
jdx = np.tile(np.arange(len(yp)), len(yp))
s = yp[[idx]] - yp[[jdx]]

这基本上创建了一个索引网格，然后我使用它.idx=[0,0,0,1,1,1,...] 而 jdx=[0,1,2,0,1,2...]代码>.不知道有没有更简单的方法...

This basically create a indexing mesh which I then use. idx=[0,0,0,1,1,1,...] while jdx=[0,1,2,0,1,2...]. I do not know if there is a simpler manner of doing it...

无论如何，TensorFlow 有一个 tf.tile()，但它似乎缺少一个 tf.repeat().

Anyhow, TensorFlow has a tf.tile(), but it seems to be lacking a tf.repeat().

idx = np.repeat(np.arange(n), n)
v2 = v[idx]

我得到了错误:

TypeError: Bad slice index [  0   0   0 ..., 215 215 215] of type <type 'numpy.ndarray'>

使用 TensorFlow 常量进行索引也不起作用:

It also does not work to use a TensorFlow constant for the indexing:

idx = tf.constant(np.repeat(np.arange(n), n))
v2 = v[idx]

-

TypeError: Bad slice index Tensor("Const:0", shape=TensorShape([Dimension(46656)]), dtype=int64) of type <class 'tensorflow.python.framework.ops.Tensor'>

这个想法是转换我的RankNet 实现到 TensorFlow.

The idea is to convert my RankNet implementation to TensorFlow.

推荐答案

使用tf.tile() 和 tf.reshape():

idx = tf.range(len(yp))
idx = tf.reshape(idx, [-1, 1])    # Convert to a len(yp) x 1 matrix.
idx = tf.tile(idx, [1, len(yp)])  # Create multiple columns.
idx = tf.reshape(idx, [-1])       # Convert back to a vector.

您可以使用 tf.tile() 简单地计算 jdx:

You can simply compute jdx using tf.tile():

jdx = tf.range(len(yp))
jdx = tf.tile(jdx, [len(yp)])

对于索引，您可以尝试使用 tf.gather() 从 yp 张量中提取非连续切片:

For the indexing, you could try using tf.gather() to extract non-contiguous slices from the yp tensor:

s = tf.gather(yp, idx) - tf.gather(yp, jdx)

这篇关于TensorFlow:numpy.repeat() 替代方案的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！