The post process for Differentiable Binarization (DB).

Balanced CrossEntropy Loss on `binary`, MaskL1Loss on `thresh`, DiceLoss on `thresh_binary`. Note: The meaning of inputs can be figur

Balanced cross entropy loss. Shape: - Input: :math:`(N, 1, H, W)` - GT: :math:`(N, 1, H, W)`, same shape as the input

r''' Making binary mask from detection data with ICDAR format. Typically following the process of class `MakeICDARData`.

Loss function from https://arxiv.org/abs/1707.03237, where iou computation is introduced heatmap manner to measure the diversity bwtween

DiceLoss normalized on each instance. Input: pred: (N, 1, H, W) gt: (N, 1, H, W) mask: (N, H, W) Note: This class

Variation from DiceLoss. The coverage and union are computed separately.