Implementation of the GELU activation function currently in Google BERT repo (identical to OpenAI GPT). Also see the Gaussian Error Linear Un

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

Get image ids that satisfy given filter conditions. default skips that filter :param quesIds (int array) : get image ids for gi

box_size: [x1,x2,...,xn,3] heading_angle: [x1,x2,...,xn] center: [x1,x2,...,xn,3] Return: [x1,x3,...,xn,8,3]

Given a file, get the size of file in MB

Compute IoU of two bounding boxes. ** Define your bod IoU function HERE **

Args: clip (torch.tensor): Video clip to be normalized. Size is (C, T, H, W) Returns: flipped clip (torch.tensor): Size is (C

Load questions and answers with the specified question ids. :param ids (int array) : integer ids specifying question ids

Load from config files.

Example >>> dataset = load_dataset("coco_caption", cfg=None) >>> splits = dataset.keys() >>> print([len(dataset[split]) for split in

Common i/o utility to handle loading data from various file formats. Supported: .pkl, .pickle, .npy, .json For the npy files, we

Load supported models. To list all available models and types in registry: >>> from lavis.models import model_zoo >>> print(model_zo

Load model and its related preprocessors. List all available models and types in registry: >>> from lavis.models import model_zoo >>

Example >>> processor = load_processor("alpro_video_train", cfg=None)

Load tf checkpoints in a pytorch model.

A property to get and create learning rate scheduler by split just in need.

https://github.com/allenai/allennlp/blob/master/allennlp/nn/util.py#L278-L309

Merge configs from a list.

Args: labels: (B, N, 6) pred: (B, M, 6) iou_thresh: scalar conf_thresh: scalar label_mask: (B, N,) with v

Args: clip (torch.tensor): Video clip to be normalized. Size is (C, T, H, W) mean (tuple): pixel RGB mean. Size is (3) st