elektronn3.modules.lovasz_losses module

Lovasz-Softmax and Jaccard hinge loss in PyTorch Maxim Berman 2018 ESAT-PSI KU Leuven (MIT License)

elektronn3.modules.lovasz_losses.binary_xloss(logits, labels, ignore=None)

Binary Cross entropy loss

logits: [B, H, W] Variable, logits at each pixel (between -infty and +infty) labels: [B, H, W] Tensor, binary ground truth masks (0 or 1) ignore: void class id

elektronn3.modules.lovasz_losses.flatten_binary_scores(scores, labels, ignore=None)

Flattens predictions in the batch (binary case) Remove labels equal to ‘ignore’

elektronn3.modules.lovasz_losses.flatten_probas(probas, labels, ignore=None)

Flattens predictions in the batch

elektronn3.modules.lovasz_losses.iou(preds, labels, C, EMPTY=1.0, ignore=None, per_image=False)

Array of IoU for each (non ignored) class

elektronn3.modules.lovasz_losses.iou_binary(preds, labels, EMPTY=1.0, ignore=None, per_image=True)

IoU for foreground class binary: 1 foreground, 0 background

elektronn3.modules.lovasz_losses.lovasz_grad(gt_sorted)

Computes gradient of the Lovasz extension w.r.t sorted errors See Alg. 1 in paper

elektronn3.modules.lovasz_losses.lovasz_hinge(logits, labels, per_image=True, ignore=None)

Binary Lovasz hinge loss

logits: [B, H, W] Variable, logits at each pixel (between -infty and +infty) labels: [B, H, W] Tensor, binary ground truth masks (0 or 1) per_image: compute the loss per image instead of per batch ignore: void class id

elektronn3.modules.lovasz_losses.lovasz_hinge_flat(logits, labels)

Binary Lovasz hinge loss

logits: [P] Variable, logits at each prediction (between -infty and +infty) labels: [P] Tensor, binary ground truth labels (0 or 1) ignore: label to ignore

elektronn3.modules.lovasz_losses.lovasz_softmax(probas, labels, only_present=False, per_image=False, ignore=None)

Multi-class Lovasz-Softmax loss

probas: [B, C, H, W] Variable, class probabilities at each prediction (between 0 and 1) labels: [B, H, W] Tensor, ground truth labels (between 0 and C - 1) only_present: average only on num_classes present in ground truth per_image: compute the loss per image instead of per batch ignore: void class labels

elektronn3.modules.lovasz_losses.lovasz_softmax_flat(probas, labels, only_present=False)

Multi-class Lovasz-Softmax loss

probas: [P, C] Variable, class probabilities at each prediction (between 0 and 1) labels: [P] Tensor, ground truth labels (between 0 and C - 1) only_present: average only on num_classes present in ground truth

elektronn3.modules.lovasz_losses.mean(l, ignore_nan=False, empty=0)

nanmean compatible with generators.

elektronn3.modules.lovasz_losses.xloss(logits, labels, ignore=None)

Cross entropy loss