nanmean compatible with generators.

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: [P, C] Variable, class probabilities at each prediction (between 0 and 1) labels: [P] Tensor,

r"""Returns the state of SWA as a :class:`dict`. It contains three entries: * opt_state - a dict holding current optimization sta

r"""Performs a single optimization step. In automatic mode also updates SWA running averages.

r"""Updates the SWA running averages for the given parameter group. Arguments: param_group (dict): Specifies for what parameter g

r"""Loads the optimizer state. Args: state_dict (dict): SWA optimizer state. Should be an object returned from a

r"""Swaps the values of the optimized variables and swa buffers. It's meant to be called in the end of training to use the collected

r"""Implements Stochastic Weight Averaging (SWA). Stochastic Weight Averaging was proposed in `Averaging Weights Leads to Wider Optim

r"""Add a param group to the :class:`Optimizer` s `param_groups`. This can be useful when fine tuning a pre-trained network as frozen

Binary Cross entropy loss logits: [B, H, W] Variable, logits at each pixel (between -\infty and +\infty) labels: [B, H, W] Tensor, bi

r"""Updates BatchNorm running_mean, running_var buffers in the model. It performs one pass over data in `loader` to estimate the activation

Array of IoU for each (non ignored) class

IoU for foreground class binary: 1 foreground, 0 background

Binary Lovasz hinge loss logits: [B, H, W] Variable, logits at each pixel (between -\infty and +\infty) labels: [B, H, W] Tensor, bin

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

r"""Updates the SWA running averages of all optimized parameters.

Cross entropy loss