Save the current checkpoint and delete unwanted checkpoint.

Save the best checkpoint. It will compare the score according to the compare function, write related information (best score, best ch

Saving the results in the format required for leaderboard evaluation. [TODO] add support for multi-choice.

Rescale a size by a ratio. Args: size (tuple[int]): (w, h). scale (float | tuple(float)): Scaling factor. Returns: t

Judge whether to perform evaluation. Here is the rule to judge whether to perform evaluation: 1. It will not perform evaluation durin

Swap the parameter of model with parameter in ema_buffer.

An inner training loop compatible with both epoch-based and iter-based training. When using epoch-based, training stops after one ep

Allreduce gradients. Args: params (list[torch.Parameters]): List of parameters of a model coalesce (bool, optional): Whether allr

Clip bboxes to fit the image shape. Args: bboxes (ndarray): Shape (..., 4*k) img_shape (tuple[int]): (height, width) of the image

Convert a BGR image to grayscale image. Args: img (ndarray): The input image. keepdim (bool): If False (by default), then return

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataload

Build datasets.

Builder for drop out layers.

Build loss.

Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you

Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you

This implementation downloads the remote resource and caches it locally. The resource will only be downloaded if not previously requested.

A decorator factory to check if prerequisites are satisfied. Args: prerequisites (str of list[str]): Prerequisites to be checked.

Concatenates multiple datasets into a single dataset. It supports may-style datasets and DataPipeline from WebDataset. Currently, does not s

Contrast distortion.

3x3 convolution with padding.

Convert applicable model parameters to fp16

Convert applicable model parameters to fp16

Copy gradients from fp16 model to fp32 weight copy.

Copy updated params from fp32 weight copy to fp16 model.

Create dataloaders for training and validation.

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

Get current learning rates. Returns: list[float] | dict[str, list[float]]: Current learning rates of all param gr

tpMap: center: tpMap[1, 0, :, :] displacement: tpMap[1, 1:5, :, :]

Denormalize input grid from range [0, 1] to [-1, 1] Args: grid (Tensor): The grid to be denormalize, range [0, 1]. Returns: Te

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for Ef

Evaluate the dataset. Args: results (list): Testing results of the dataset. metric (str | list[str]): Metrics to be e

Extract features from images.

Flattens predictions in the batch (binary case) Remove labels equal to 'ignore_index'.

Flattens predictions in the batch.

Convert FLOPs number into a string. Note that Here we take a multiply-add counts as one FLOP. Args: flops (float): FLOPs number to b

Placeholder of forward function.

Forward function.

Placeholder of forward function.

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

Scatters points into voxels. Args: points (torch.Tensor): Points to be reduced into voxels. coors (torch.Tensor): Cor

Generate config from config str. Args: cfg_str (str): Config str. file_format (str): Config file format corresponding

Read data from a given ``filepath`` with 'rb' mode. Args: filepath (str or Path): Path to read data. Returns:

Get question ids that satisfy given filter conditions. default skips that filter :param imgIds (int array) : get question ids f

Randomly get a crop bounding box.

return info dicts for specified keys (or all if None) at specified indices (or out_indices if None)

Get frame by index. Args: frame_id (int): Index of the expected frame, 0-based. Returns: ndarray or None: Re

Get hostname and username. Return empty string if exception raised, e.g. ``getpass.getuser()`` will lead to error in docker container

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 handl

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 handl

Calculate parameter number of a model. Args: model (nn.module): The model for parameter number calculation. Returns: float: