Denotes the total number of samples

Denotes the total number of samples

Denotes the total number of samples

Denotes the total number of samples

Denotes the total number of samples

Denotes the total number of samples

Add bounding box to visualizer. Args: bbox3d (numpy.array, shape=[M, 7]): 3D bbox (x, y, z, x_size, y_size, z_size

Add segmentation mask to visualizer via per-point colorization. Args: seg_mask_colors (numpy.array, shape=[N, 6]):

Add segmentation mask to visualizer via per-point colorization. Args: seg_mask_colors (numpy.array, shape=[N, 6]):

Cosine anneal from `start` to `end` as pct goes from 0.0 to 1.0.

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

Reset the state of the inner optimizer.

Colorize pointcloud with the color of each semantic label.

Compute foreground mask for images Args: gt_boxes2d: (B, N, 4), 2D box labels shape: torch.Size or tuple, Foreground mask des

Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.

Create an `optim.Optimizer` from `opt_func` with `lr`. Set lr on `layer_groups`.

Same usage method as nn.CrossEntropyLoss: >>> criteria = LabelSmoothSoftmaxCEV1() >>> logits = torch.randn(8, 19, 384

Args: input: (B, #anchors, #classes) float tensor. Predicted logits for each class target: (B, #ancho

Args: input: (B, #anchors, #codes) float tensor. Ecoded predicted locations of objects. target: (B, #

Args: input: (B, #anchors, #codes) float tensor. Ecoded predicted locations of objects. target: (B, #

Args: input: (B, #anchors, #classes) float tensor. Predited logits for each class. target: (B, #ancho

Args: output: (batch x dim x h x w) or (batch x max_objects) mask: (batch x max_objects) ind: (batch x ma

args: feat: torch.Float32 tensor N X C count_map: int max batch size pxpy: torch.Int32 tensor N X 3 (mea

args: pxpy: torch.Int32 tensor N X 3 (mean batch_id, px, py) px range:0~w py range:0~h

Forward pass. :param predictions: <torch.FloatTensor: n_samples, C, H, W>. Predicted scores. :param targets: <torch.LongTenso

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

Input: - pred: the output from model (before softmax), shape (N, C, H, W) - gt: ground truth map, shape (N, H, w)

Arguments: - strategy: RangeAug strategies. - image: original image, size: [bs, 6, h, w]. - label: origin

Arguments: - strategy: MixTeacher strategies. - image: original image, size: [6, H, W]. - label: original