metrics

DiceScore

Bases: CatMetric

torch.nn.Module for dice loss (given by :math:D(p, t) = \frac{2|pt|+s}{|p|+|t|+s}) computation.

Parameters:

Name	Type	Description	Default
smooth	float	smooth value for dice score.	1
reduction	str	reduction method for computed dice scores. Can be one of "mean", "sum" or "none".	'mean'

dice_score(input, target, smooth=1, reduction='mean')

Computes dice score (given by :math:D(p, t) = \frac{2|pt|+s}{|p|+|t|+s}) between predicted input tensor and target ground truth.

Parameters:

Name	Type	Description	Default
input	torch.Tensor	predicted input tensor of shape (N, ...).	required
target	torch.Tensor	target ground truth tensor of shape (N, ...).	required
smooth	float	smooth value for dice score.	1
reduction	str	reduction method for computed dice scores. Can be one of "mean", "sum" or "none".	'mean'

Returns:

Type	Description
torch.Tensor	Computed dice score, optionally reduced using specified reduction method.