Args: x: 4 channel rgb+mask

Args: x: 4 channel rgb+mask

Args: x: 4 channel rgb+mask

Apply gaussian filter to input. Arguments: input (torch.Tensor): Input to apply gaussian filter on. Returns:

image: (1, 3, H, W) torch.uint8 Tensor mask: (1, 1, H, W) torch.uint8 Tensor

Given a type name string (or an object having a __name__ attribute), return matching Numpy and ctypes types that have the same size in bytes.

Get the directory path of the module containing the given object name.

Return the fully-qualified name of a top-level function.

r"""Register an import hook that is called whenever a persistent object is being unpickled. A typical use case is to patch the pickled source

Args: module: [nn.module] list or nn.module a list of module to be initialized.

r"""Initializes `torch_utils.training_stats` for collecting statistics across multiple processes. This function must be called after `tor

List all files recursively in a given directory while ignoring given file and directory names. Returns list of tuples containing both absolute and

Download the given URL and return a binary-mode file object to access the data.

r"""Broadcasts the given set of scalars by the first process (`rank = 0`), but ignores any scalars provided by the other processes. See `repor

Count flops for the rfft/rfftn operator. Source: https://github.com/raoyongming/DynamicViT/blob/master/calc_flops.py