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,

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

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

nanmean compatible with generators.

nanmean compatible with generators.

Create a new `OptimWrapper` from `self` with another `layer_groups` but the same hyper-parameters.

:param predictions: NCHW :param pxpy: Nx3 3: batch_idx, px, py :return:

Set points for label not from file but from numpy.

Return list of trainable params in `m`.

ResNet-34 model from "Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>

To support a custom dataset, implement this function to load the raw data (and labels), then transform them to the unified normative

Dice loss for one channel binarized input. :param predictions: <torch.FloatTensor: n_samples, 1, H, W>. Predicted scores. :pa

Dice loss for one channel binarized input. :param predictions: <torch.FloatTensor: n_samples, 1, H, W>. Predicted scores. :pa

Calculate the loss for multichannel predictions. :param predictions: <torch.FloatTensor: n_samples, n_class, H, W>. Predicted scores.

Calculate the loss for multichannel predictions. :param predictions: <torch.FloatTensor: n_samples, n_class, H, W>. Predicted scores.

Refer to https://github.com/tianweiy/CenterPoint L1 regression loss Args: regr (batch x max_objects x dim) gt_regr (batch

Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[data]