MaskedDiceLoss¶

class mmocr.models.common.MaskedDiceLoss(eps=1e-06)[source]¶

Masked dice loss.

Parameters: eps (float, optional) – Eps to avoid zero-divison error. Defaults to 1e-6.
Return type: None

forward(pred, gt, mask=None)[source]¶

Forward function.

Parameters

pred (torch.Tensor) – The prediction in any shape.
gt (torch.Tensor) – The learning target of the prediction in the same shape as pred.
mask (torch.Tensor, optional) – Binary mask in the same shape of pred, indicating positive regions to calculate the loss. Whole region will be taken into account if not provided. Defaults to None.

Returns

The loss value.

Return type

torch.Tensor