是否有 TensorFlow.js 方法可以在特定位置将张量添加到另一个张量？

Question

Let me make the question clear. I have a tensor, just to keep it simple, with zeros. A 2D tensor with shape [3, 3] , call it a :

[[0,0,0],
 [0,0,0],
 [0,0,0]]

And I have another tensor, a 2D tensor with shape [2, 2] , call it b , and its just ones:

[[1,1],
 [1,1]]

I want to add them together, but their shapes don't match, and I can't broadcast it as well, but it's not the goal. I want the result of:

[[0,0,0],
 [0,1,1],
 [0,1,1]]

And if there would be a method, call it insert for now, I'd have to specify the location where I want to insert the smaller tensor (just as when slicing, defining the start location). It would look something like this:

a.insert(b, [1, 1])

I was thinking about pad which could produce similar results, but if there would be something like the above, what I might missed, it would be nicer.

Answer 1

使用tf.pad ，可以按如下方式完成

padded = tf.ones([2, 2]).pad([[1, 0], [1, 0]])