Dice Loss, there are two forms of dice loss is supported: - the one proposed in `V-Net: Fully Convolutional Neural Networ

`Focal Loss <https://arxiv.org/abs/1708.02002>`_ Args: use_sigmoid (bool, optional): Whether to the prediction is

str: a string that describes the module

str: a string that describes the module

Compute classification and mask targets for one image. Args: cls_score (Tensor): Mask score logits from a single decoder layer

Compute classification and mask targets for one image. Args: cls_score (Tensor): Mask score logits from a single decoder layer

Sample negative samples.

Sample positive samples.

Add all parameters of module to the params list. The parameters of the given module will be added to the list of param groups, with s

Add all parameters of module to the params list. The parameters of the given module will be added to the list of param groups, with s

Apply all reduce function for python dict object. The code is modified from https://github.com/Megvii- BaseDetection/YOLOX/blob/main/yolox/ut

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

Computes one-to-one matching based on the weighted costs. This method assign each query prediction to a ground truth or background. T

Test with augmentations. Only rescale=True is supported.

Test with augmentations. Only rescale=True is supported.

torch.Tensor: concatenated positive and negative boxes

Calculate the binary CrossEntropy loss. Args: pred (torch.Tensor): The prediction with shape (N, 1). label (torch.Tensor): The le

Builder of box coder.

Build Transformer.

cross_entropy. The wrapper function for :func:`F.cross_entropy` Args: pred (torch.Tensor): The prediction with shape (N, 1). labe

Encode bitmap mask to RLE code. Args: mask_results (list | tuple[list]): bitmap mask results. In mask scoring rcnn, mask_resu

Extra repr.

:param query (N, Length_{query}, C) :param reference_points (N, Length_{query}, n_levels, 2), range

Forward function.