torch / nn / torch.nn
PairwiseDistance¶
-
class
torch.nn.
PairwiseDistance
(p: float = 2.0, eps: float = 1e-06, keepdim: bool = False)[source]¶ Computes the batchwise pairwise distance between vectors , using the p-norm:
- Parameters
- Shape:
Input1: where D = vector dimension
Input2: , same shape as the Input1
Output: . If
keepdim
isTrue
, then .
- Examples::
>>> pdist = nn.PairwiseDistance(p=2) >>> input1 = torch.randn(100, 128) >>> input2 = torch.randn(100, 128) >>> output = pdist(input1, input2)
此页内容是否对您有帮助