python - PyTorch 获取二维张量中的值索引

Question

给定以下张量(或任何具有二维的随机张量)，我想获得“101”的索引:

tens = tensor([[  101,   146,  1176, 21806,  1116,  1105, 18621,   119,   102,     0,
             0,     0,     0],
        [  101,  1192,  1132,  1136,  1184,   146,  1354,  1128,  1127,   117,
          1463,   119,   102],
        [  101,  6816,  1905,  1132, 14918,   119,   102,     0,     0,     0,
             0,     0,     0]])

从相关的答案我知道我可以做这样的事情:

idxs = torch.tensor([(i == 101).nonzero() for i in tens])

但这看起来很困惑，而且可能很慢。有没有更好的方法来做到这一点，它既快速又更具火炬感？

仅讨论一维张量的相关问题:

How Pytorch Tensor get the index of specific value

How Pytorch Tensor get the index of elements?

Answer 1

怎么样(tens == 101).nonzero()[:, 1]

In [20]: from torch import tensor                                                                       

In [21]: tens = torch.tensor([[  101,   146,  1176, 21806,  1116,  1105, 18621,   119,   102,     0, 
    ...:              0,     0,     0], 
    ...:         [  101,  1192,  1132,  1136,  1184,   146,  1354,  1128,  1127,   117, 
    ...:           1463,   119,   102], 
    ...:         [  101,  6816,  1905,  1132, 14918,   119,   102,     0,     0,     0, 
    ...:              0,     0,     0]])                                                                

In [22]: (tens == 101).nonzero()[:, 1]                                                                  
Out[22]: tensor([0, 0, 0])