Assume the first argument is the name of the argument.

r"""Get an item from registry with key 'name' Args: name (string): Key whose value needs to be retrieved. default: If

Print information about the VQA annotation file. :return:

Loads the schedulers state. Arguments: state_dict (dict): scheduler state. Should be an object returned from a cal

Build a pretrained model from default configuration file, specified by model_type. Args: - model_type (str): model type,

Returns the state of the scheduler as a :class:`dict`. It contains an entry for every variable in self.__dict__ which is not the optim

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

Download a file from a URL and cache it locally. If the file already exists, it is not downloaded again. If distributed, only the main proces

Input: pc1: (B,N,C) torch tensor pc2: (B,M,C) torch tensor l1smooth: bool, whether to use l1smooth loss delta: sc

r"""Register a path to registry with key 'name' Args: name: Key with which the path will be registered. Usage:

Compute P and R for predicted bounding boxes. Ignores classes! Args: labels: (N x bbox) ground-truth bounding boxes (6 dims) pred

Computes IoU of two axis aligned bboxes. Args: box_a, box_b: 6D of center and lengths Returns: iou

Download a file from a url and place it in root. Args: url (str): URL to download file from root (str): Directory to place downloa

Args: samples (dict): A dictionary containing the following keys: - image (torch.Tensor): A tensor of shape (batc

Inverse function to angle2class. As ScanNet only has axis-alined boxes so angles are always 0.

Inverse function to size2class

Evaluate the model on a given split. Args: split_name (str): name of the split to evaluate on. cur_epoch (in

Makes broadcastable attention and causal masks so that future and masked tokens are ignored. Arguments: attention_mask (

Args: error: Torch tensor (d1,d2,...,dk) Returns: loss: Torch tensor (d1,d2,...,dk) x = error = pred - gt or dist(pred,g

Load result file and return a result object. :param resFile (str) : file name of result file :return: res (obj)

Load checkpoint as specified in the config file. If load_finetuned is True, load the finetuned model; otherwise, load the pretrained

Create the directory if it does not exist.

r"""Register an item to registry with key 'name' Args: name: Key with which the item will be registered. Usage::

Organizes datasets by split. Args: datasets: dict of torch.utils.data.Dataset objects by name. Returns: Dict of dataset

Accumulate one batch of prediction and groundtruth. Args: batch_pred_map_cls: a list of lists [[(pred_cls, pred_box_para