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

Read data from a given ``filepath`` with 'r' mode. Args: filepath (str or Path): Path to read data. encoding (str): T

Resize image to a given size. Args: img (ndarray): The input image. size (tuple[int]): Target size (w, h). return_scale (

Show an image. Args: img (str or ndarray): The image to be displayed. win_name (str): The window name. wait_time (int): V

Write image to file. Args: img (ndarray): Image array to be written. file_path (str): Image file path. params (None or li

Inference with slide/whole style. Args: img (Tensor): The input image of shape (N, 3, H, W). img_meta (dict): Image i

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

load checkpoint through HTTP or HTTPS scheme path. In distributed setting, this function only download checkpoint at local rank 0. Args:

make plugins for block. Args: in_channels (int): Input channels of plugin. plugins (list[dict]): List of plugins cfg

Create the directory if it does not exist.

nn.Module: normalization layer after the third convolution layer

batch_pc: BxNx3

Randomly scale the point cloud. Scale is per point cloud. Input: BxNx3 array, original batch of point clouds Return:

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

Randomly perturb the point clouds by small rotations Input: BxNx3 array, original batch of point clouds Return: B

Randomly rotate the point clouds to augument the dataset rotation is per shape based along up direction Input: BxNx3 array,

Randomly shift point cloud. Shift is per point cloud. Input: BxNx3 array, original batch of point clouds Return:

r"""Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distributi

Warmup the learning rate

vis_root (string): Root directory of images (e.g. coco/images/) ann_root (string): directory to store the annotation file spl

vis_root (string): Root directory of images (e.g. coco/images/) ann_root (string): directory to store the annotation file

vis_root (string): Root directory of images (e.g. coco/images/) ann_root (string): directory to store the annotation file

Since built-in ``any`` works only when the element of iterable is not iterable, implement the function.

perform evaluation and save ckpt.

Download annotation files if necessary. All the vision-language datasets should have annotations of unified format. storage_

Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.

Freeze stages param and norm stats.

Sample from fine grained features. Args: prev_output (list[Tensor]): Prediction of previous decode head. points (Tens

Sample from fine grained features. Args: x (list[Tensor]): Feature pyramid from by neck or backbone. points (Tensor):

Group keys based on common prefixes. A prefix is the string up to the final "." in each key. Args: keys (list[str]): list of para

Format a group of parameter name suffixes into a loggable string. Args: group (list[str]): list of parameter name suffixes. Retur

Initialize rule, key_indicator, comparison_func, and best score. Here is the rule to determine which rule is used for key indicator w

Override default load function. AWS overrides the function _load_from_state_dict to recover weight_gamma and weight_beta if they are

merge dict ``a`` into dict ``b`` (non-inplace). Values in ``a`` will overwrite ``b``. ``b`` is copied first to avoid in-place modific

Convert a pillow image to numpy array. Args: img (:obj:`PIL.Image.Image`): The image loaded using PIL flag (str): Flags specifyin

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