dgs.models.metric.metric.EuclideanSquareMetric

class dgs.models.metric.metric.EuclideanSquareMetric(*args: Any, **kwargs: Any)

Class to compute the squared Euclidean distance between two matrices.

Methods

__init__(*args: Any, **kwargs: Any) → None

static forward(input1: torch.Tensor, input2: torch.Tensor) → torch.Tensor

Compute squared Euclidean distance between two matrices with a matching second dimension.

Parameters:

• input1 – tensor of shape [a x E]

• input2 – tensor of shape [b x E]

Returns:

tensor of shape [a x b] containing the distances.