Save the checkpoint at the current epoch.

Performs all_gather operation on the provided tensors. Graph remains connected for backward grad computation.

Average latest n values or all values.

Build projection layer for key/query/value/out.

Crop from ``img``

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

Calculate evaluation metrics Args: results (list[ndarray] | list[str]): List of prediction segmentation maps or list of predic

Evaluate the results. Args: runner (:obj:`mmcv.Runner`): The underlined training runner. results (list): Output resul

Input: xyz: pointcloud data, [N, D] npoint: number of samples Return: centroids: sampled pointcloud index, [npoint, D

Get the registry record. Args: key (str): The class name in string format. Returns: class: The corresponding

Get value by key at specified index (indices) if idx == None, returns value for key at each output index if idx is an integer, return

Initialize and get a logger by name. If the logger has not been initialized, this method will initialize the logger by adding one or two hand

Read an image. Args: img_or_path (ndarray or str or Path): Either a numpy array or str or pathlib.Path. If it is a numpy arra

This function checks if the provided value can be serialized into a JSON string.

Make divisible function. This function rounds the channel number to the nearest value that can be divisible by the divisor. It is taken from

Save ndarray to local numpy file. Args: array (ndarray): Ndarray to save. temp_file_name (str): Numpy file name. If 'temp_file_na

Wraps modules and applies quantization noise to the weights for subsequent quantization with Iterative Product Quantization as described

Scatter with support for kwargs dictionary.

Convert objects of various python types to :obj:`torch.Tensor`. Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`, :class:`S

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

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

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

This function is taken from the original tf repo. It ensures that all layers have a channel number that is divisible by 8 It can be seen

This function is taken from the original tf repo. It ensures that all layers have a channel number that is divisible by 8 It can be seen

Make each stage.

Make transition layer.

Scale the data in the corresponding channel.

Calculate accuracy according to the prediction and target. Args: pred (torch.Tensor): The model prediction, shape (N, num_class, ...)

Allreduce parameters. Args: params (list[torch.Parameters]): List of parameters or buffers of a model. coalesce (bool

Convert various input to color tuples. Args: color (:obj:`Color`/str/tuple/int/ndarray): Color inputs Returns: tuple[int]: A

Convert a video with ffmpeg. This provides a general api to ffmpeg, the executed command is:: `ffmpeg -y <pre_options> -i <in_file> <opt

Encode images with backbone and decode into a semantic segmentation map of the same size as input.

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

Placeholder for Forward function for training.

Forward function for training. Args: img (Tensor): Input images. img_metas (list[dict]): List of image info dict wher

Input: xyz: pointcloud data, [B, N, 3] npoint: number of samples Return: centroids: sampled pointcloud index, [B, npo

Converts all `BatchNorm2d` and `SyncBatchNorm` layers of provided module into `FrozenBatchNorm2d`. If `module` is itself an instance of eithe

Get the registry record. Args: key (str): The class name in string format. Returns: class: The corresponding c

Get class weight for loss function. Args: class_weight (list[float] | str | None): If class_weight is a str, take it as a fil