Return two lists, one for the model parameters in FP16 and one for the master parameters in FP32.

:param points: xyzir :return: depth_image, reflectivity_image, px(-1~1), py(-1~1)

Generates one sample of data

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

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

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: [B, C, H, W] Variable, class probabilities at each prediction (between 0 and 1). Inte

Convert class index tensor to one hot encoding tensor. Args: input: A tensor of shape [N, 1, *] num_classes: An int of number o

Convert class index tensor to one hot encoding tensor. Args: input: A tensor of shape [N, 1, *] num_classes: An int of number o

Copy `master_params` to `model_params`.

Copy the `model_params` gradients to `master_params` for the optimizer step.

Return One Hot Label

Return One Hot Label

Read the values inside the optimizer for the hyper-parameters.

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

Reset scan members.

Set scan attributes (instead of opening from file).

Visualize the points cloud. Args: save_path (str, optional): path to save image. Default: None.

PyTorch Implementation for tf.nn.sigmoid_cross_entropy_with_logits: max(x, 0) - x * z + log(1 + exp(-abs(x))) in https://www.