在TensorFlow中，函数'tf.one_hot'中的参数'axis'是什么 [英] In TensorFlow, what is the argument 'axis' in the function 'tf.one_hot'

问题描述

有人可以帮忙解释一下 TensorFlow 的 one_hot 函数中的 axis 吗?

Could anyone help with an an explanation of what axis is in TensorFlow's one_hot function?

根据文档:

axis:要填充的轴(默认值:-1，一个新的最里面的轴)

axis: The axis to fill (default: -1, a new inner-most axis)

最近，我在 SO是与之相关的解释上得到了答案.熊猫:

Closest I came to an answer on SO was an explanation relevant to Pandas:

不确定上下文是否同样适用.

Not sure if the context is just as applicable.

推荐答案

下面是一个示例:

x = tf.constant([0, 1, 2])

...是输入张量， N = 4 (每个索引都转换为4D向量).

... is the input tensor and N=4 (each index is transformed into 4D vector).

计算 one_hot_1 = tf.one_hot(x，4).eval()产生一个(3，4)张量:

[[ 1.  0.  0.  0.]
 [ 0.  1.  0.  0.]
 [ 0.  0.  1.  0.]]

...，其中最后一个尺寸是一维编码的(清晰可见).这对应于默认的 axis = -1 ，即 last 之一.

... where the last dimension is one-hot encoded (clearly visible). This corresponds to the default axis=-1, i.e. the last one.

现在，计算 one_hot_2 = tf.one_hot(x，4，axis = 0).eval()产生一个(4，3)张量，它不是立即可识别为一键编码:

Now, computing one_hot_2 = tf.one_hot(x, 4, axis=0).eval() yields a (4, 3) tensor, which is not immediately recognizable as one-hot encoded:

[[ 1.  0.  0.]
 [ 0.  1.  0.]
 [ 0.  0.  1.]
 [ 0.  0.  0.]]

这是因为单热编码是沿着0轴完成的，因此必须转置矩阵才能看到以前的编码.当输入的维数较高时，情况会变得更加复杂，但思想是相同的:区别在于用于一键编码的 extra 维的位置.

This is because the one-hot encoding is done along the 0-axis and one has to transpose the matrix to see the previous encoding. The situation becomes more complicated, when the input is higher dimensional, but the idea is the same: the difference is in placement of the extra dimension used for one-hot encoding.

这篇关于在TensorFlow中，函数'tf.one_hot'中的参数'axis'是什么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！