Pytorch Tensor如何获取特定值的索引

Question

有了 python 个列表，我们可以做：

a = [1, 2, 3]
assert a.index(2) == 1

pytorch 张量如何直接找到 .index()？

Answer 1

我认为没有从 list.index() 到 pytorch 函数的直接翻译。但是，您可以使用 tensor==number 然后使用 nonzero() 函数获得类似的结果。例如：

t = torch.Tensor([1, 2, 3])
print ((t == 2).nonzero(as_tuple=True)[0])

这段代码returns

1

[torch.LongTensor of size 1x1]

Answer 2

可以通过如下转换为numpy来完成

import torch
x = torch.range(1,4)
print(x)
===> tensor([ 1.,  2.,  3.,  4.]) 
nx = x.numpy()
np.where(nx == 3)[0][0]
===> 2

Answer 3

    import torch
    x_data = variable(torch.Tensor([[1.0], [2.0], [3.0]]))
    print(x_data.data[0])
    >>tensor([1.])

Answer 4

对于浮点张量，我用这个来获取张量中元素的索引

print((torch.abs((torch.max(your_tensor).item()-your_tensor))<0.0001).nonzero())

这里我想获取max_value在float tensor中的索引，你也可以这样输入你的值来获取tensor中任意元素的索引

print((torch.abs((YOUR_VALUE-your_tensor))<0.0001).nonzero())

Answer 5

用于查找 1d 中元素的索引 tensor/array 例子

mat=torch.tensor([1,8,5,3])

找到索引 5

five=5

numb_of_col=4
for o in range(numb_of_col):
   if mat[o]==five:
     print(torch.tensor([o]))

查找 2d/3d 张量的元素索引将其转换为 1d #ie example.view（元素个数）

示例

mat=torch.tensor([[1,2],[4,3])
#to find index of 2

five = 2
mat=mat.view(4)
numb_of_col = 4
for o in range(numb_of_col):
   if mat[o] == five:
     print(torch.tensor([o]))

Answer 6

对于多维张量你可以这样做：

(tensor == target_value).nonzero(as_tuple=True)

生成的张量的形状为 number_of_matches x tensor_dimension。例如，假设 tensor 是一个 3 x 4 张量（这意味着维度为 2），结果将是一个二维张量，其中包含行中匹配项的索引。

tensor = torch.Tensor([[1, 2, 2, 7], [3, 1, 2, 4], [3, 1, 9, 4]])
(tensor == 2).nonzero(as_tuple=False)
>>> tensor([[0, 1],
        [0, 2],
        [1, 2]])

Answer 7

根据其他人的回答：

t = torch.Tensor([1, 2, 3])
print((t==1).nonzero().item())

Answer 8

已经给出的答案很好，但是当我在没有匹配的情况下尝试时，它们无法处理。为此，请参阅：

def index(tensor: Tensor, value, ith_match:int =0) -> Tensor:
    """
    Returns generalized index (i.e. location/coordinate) of the first occurence of value
    in Tensor. For flat tensors (i.e. arrays/lists) it returns the indices of the occurrences
    of the value you are looking for. Otherwise, it returns the "index" as a coordinate.
    If there are multiple occurences then you need to choose which one you want with ith_index.
    e.g. ith_index=0 gives first occurence.

    Reference: 
    :return:
    """
    # bool tensor of where value occurred
    places_where_value_occurs = (tensor == value)
    # get matches as a "coordinate list" where occurence happened
    matches = (tensor == value).nonzero()  # [number_of_matches, tensor_dimension]
    if matches.size(0) == 0:  # no matches
        return -1
    else:
        # get index/coordinate of the occurence you want (e.g. 1st occurence ith_match=0)
        index = matches[ith_match]
        return index

归功于这个出色的答案：

Answer 9

x = torch.Tensor([11, 22, 33, 22])
print((x==22).nonzero().squeeze())

tensor([1, 3])

Pytorch Tensor如何获取特定值的索引

How Pytorch Tensor get the index of specific value

python

pytorch