dgs.models.metric.metric¶
Methods for handling the computation of distances and other metrics.
Module Functions
|
Compute the accuracies of a predictor over a tuple of |
|
Compute the cumulative matching characteristics metric. |
|
Compute the number of correct predictions within a margin of k percent for all k. |
|
See https://github.com/pytorch/pytorch/issues/104564#issuecomment-1625348908 |
Module Classes
|
Class to compute the cosine distance between two matrices. |
|
Class to compute the cosine similarity between two matrices. |
|
Class to compute the Euclidean distance between two matrices. |
|
Class to compute the squared Euclidean distance between two matrices. |
|
Class to compute the intersection-over-union distance. |
|
Class to compute the Softmax distribution of the negative Euclidean distance. |
Class to compute the Softmax distribution of the negative squared Euclidean distance. |
|
|
Class to compute the pairwise distance. |
|
Call TorchReid's version of the cosine distance. |
|
Call TorchReid's version of the Euclidean squared distance. |