add new dementions at the front and the tail

nanmean compatible with generators.

input: grad_out: (m, c, nsample) output: (n, c), None

Set config keys via list (e.g., from command line).

r"""Helper function to convert `torch.nn.BatchNormND` layer in the model to `torch.nn.SyncBatchNorm` layer. Args: module (

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

sum over the first and last dimention

Execute an replication callback `__data_parallel_replicate__` on each module created by original replication. The callback will be invoked w

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,

Args: master_callback: a callback to be invoked after having collected messages from slave devices.

Compute the mean and standard-deviation with sum and square-sum. This method also maintains the moving average on the master device.

r"""Copies parameters and buffers from :attr:`state_dict` into only this module, but not its descendants. This is called on every submodule

Helper function to convert an arbitrary picklable python object to a tensor Returns a torch.ByteTensor representing the pickled objec

Helper function to convert a ByteTensor created by _object_to_tensor back to the picklable python object.

input: semantic_label, int, N input: ball_query_idxs, int, (nActive) input: start_len, int, (N, 2) output: cluster_idxs, int (sumNPoint, 2), dim 0 for

================================== bfs_cluster ================================== */

input: semantic_label, int, N input: ball_query_idxs, Int, (nActive) input: start_len, int, (N, 2) output: clusters, CCs