Generate the shear matrix for transformation. Args: magnitude (int | float): The magnitude used for shear. direction (str): The f

Generate the translate matrix. Args: offset (int | float): The offset used for translate. direction (str): The translate directio

If video does not exist, loop to the next one.

Check if params contain NaN.

Initialize ``auxiliary_head``

Initialize ``decode_head``

Initialize slurm distributed training environment. If argument ``port`` is not specified, then the master port will be system environment var

Check and initialize input transforms. The in_channels, in_index and input_transform must match. Specifically, when input_transform i

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Resume from a checkpoint.

Resume from a checkpoint.

Load partial pretrained model with specific prefix. Args: prefix (str): The prefix of sub-module. filename (str): Accept local fi

Load weights from .npz checkpoints for official Google Brain Flax implementation

Build multiple branch.

Make causal mask used for bi-directional self-attention.

Make causal mask used for bi-directional self-attention.

Build fuse layer.

Make each layer.

Build one branch.

Make stem layer for ResNet.

Reference: https://people.sc.fsu.edu/~jburkardt/presentations /truncated_normal.pdf

Pad images according to ``self.size``.

Pad masks according to ``results['pad_shape']``.

Parse iterable values in the string. All elements inside '()' or '[]' are treated as iterable values. Args: val (str): V

Parse the raw outputs (losses) of the network. Args: losses (dict): Raw output of the network, which usually contain

Positiong embeding method. Resize the pos_embed, if the input image size doesn't match the training size. Args:

Substitute base variable placehoders to string, so that parsing would work.

Randomly sample an img_scale according to ``ratio_range`` and ``multiscale_mode``. If ``ratio_range`` is specified, a ratio will be s

Generate the first token of answers using decoder and select ${num_ans_candidates} most probable ones. Then select answers from answe

Register a handler for some file extensions. Args: handler (:obj:`BaseFileHandler`): Handler to be registered. file_formats (str

Adapted from Mesh Tensorflow: https://github.com/tensorflow/mesh/blob/0cb87fe07da627bf0b7e60475d59f95ed6b5be3d/mesh_tensorflow/transf

Load the best checkpoint for evaluation.

TODO: add other evaluation metrics for GQA

Use official VQA evaluation script to report metrics.

Resize images with ``results['scale']``.

Resize semantic segmentation map with ``results['scale']``.

Saving the results in the format required for leaderboard evaluation.