nanmean compatible with generators.

1x1 convolution

3x3 convolution with padding

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

Flattens predictions in the batch

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

Binary Lovasz hinge loss logits: [P] Variable, logits at each prediction (between -\infty and +\infty) labels: [P] Tensor, binary gro

Multi-class Lovasz-Softmax loss probas: [B, C, H, W] Variable, class probabilities at each prediction (between 0 and 1). Inte

Multi-class Lovasz-Softmax loss probas: [P, C] Variable, class probabilities at each prediction (between 0 and 1) labels: [P] Tensor,

data augmentation from FADA and combine SimCLR (GaussianBlur & Grayscale) Args: cfg: mode: train or test is_source: i