.rst .pdf

mlreco.models.layers.cluster_cnn.losses.lovasz module

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

Original Paper: https://arxiv.org/pdf/1705.08790.pdf Github: https://github.com/bermanmaxim/LovaszSoftmax

mlreco.models.layers.cluster_cnn.losses.lovasz.lovasz_grad(gt_sorted)

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

mlreco.models.layers.cluster_cnn.losses.lovasz.iou_binary(preds, labels, EMPTY=1.0, per_image=True)

IoU for foreground class binary: 1 foreground, 0 background

mlreco.models.layers.cluster_cnn.losses.lovasz.iou(preds, labels, C, EMPTY=1.0, ignore=None, per_image=False)

Array of IoU for each (non ignored) class

mlreco.models.layers.cluster_cnn.losses.lovasz.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

mlreco.models.layers.cluster_cnn.losses.lovasz.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

mlreco.models.layers.cluster_cnn.losses.lovasz.flatten_binary_scores(scores, labels, ignore=None)

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

class mlreco.models.layers.cluster_cnn.losses.lovasz.StableBCELoss

Bases: torch.nn.modules.module.Module

__init__()

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(input, target, reduction='mean')

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

__module__ = 'mlreco.models.layers.cluster_cnn.losses.lovasz'

training: bool

mlreco.models.layers.cluster_cnn.losses.lovasz.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

mlreco.models.layers.cluster_cnn.losses.lovasz.lovasz_softmax(probas, labels, classes='present', 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).

Interpreted as binary (sigmoid) output with outputs of size [B, H, W].

labels: [B, H, W] Tensor, ground truth labels (between 0 and C - 1) classes: ‘all’ for all, ‘present’ for classes present in labels, or a list of classes to average. per_image: compute the loss per image instead of per batch ignore: void class labels

mlreco.models.layers.cluster_cnn.losses.lovasz.lovasz_softmax_flat(probas, labels, classes='present')

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) classes: ‘all’ for all, ‘present’ for classes present in labels, or a list of classes to average.

mlreco.models.layers.cluster_cnn.losses.lovasz.flatten_probas(probas, labels, ignore=None)

Flattens predictions in the batch

mlreco.models.layers.cluster_cnn.losses.lovasz.xloss(logits, labels, ignore=None)

Cross entropy loss

mlreco.models.layers.cluster_cnn.losses.lovasz.isnan(x)

mlreco.models.layers.cluster_cnn.losses.lovasz.mean(l, ignore_nan=False, empty=0)

nanmean compatible with generators.

mlreco.models.layers.cluster_cnn.losses.gs_embeddings module mlreco.models.layers.cluster_cnn.losses.misc module