Change the device of the data inplace. Example: >>> self = SamplingResult.random() >>> print(f'self = {self.to(None)}

Apply function to a list of arguments. Note: This function applies the ``func`` to multiple inputs and map the multiple outputs o

Obtain the mean of tensor on different GPUs.

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataloade

Build Match Cost.

Sample positive and negative bboxes. This is a simple implementation of bbox sampling given candidates, assigning results and ground

Decode bboxes. Args: all_cls_scores (Tensor): Outputs from the classification head, \ shape [nb_dec, bs, num_query

Set random seed. Args: seed (int): Seed to be used. deterministic (bool): Whether to set the deterministic option for

Inverse function of sigmoid. Args: x (Tensor): The tensor to do the inverse. eps (float): EPS avoid numerical

CPU version of multi-scale deformable attention. Args: value (Tensor): The value has shape (bs, num_keys, mum_heads, embed_dim

Create reduced point clouds for given info. Args: data_path (str): Path of original data. info_path (str): Path of data info.

Add prefix for dict. Args: inputs (dict): The input dict with str keys. prefix (str): The prefix to add. Returns: d

Build Assigner.

Builder for attention.

r""" Retuens annotations of the current frame. Returns ------- dict {'lane_centerline': list, 'traffic_el

Builder of box sampler.

Build Transformer.

Convert action.

During inference, the functionary of batch norm layers is turned off but only the mean and var alone channels are used, which exposes the chance t

Get a yacs CfgNode object with default values.

Test model with multiple gpus. This method tests model with multiple gpus and collects the results under two different modes: gpu and cpu mod

Performs a single optimization step. Args: closure (callable, optional): A closure that reevaluates the model and

Args: input_ch(int) : the number of input channel out_features (list[str]): name of the layers whose outputs should

r""" Calculate average precision for a vertex. Parameters ---------- gts : array_like List of vertices in shape (G, ). pr

Build optimizer, set weight decay of normalization to 0 by default.