Module to calculate the accuracy. Args: topk (tuple, optional): The criterion used to calculate the accuracy. Def

CrossEntropyLoss. Args: use_sigmoid (bool, optional): Whether the prediction uses sigmoid of softmax. Defaults to

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

Number of masks.

Number of masks.

Total number of samples of data.

Length after repetition.

Length after repetition.

str: a "nice" summary string describing this assign result

str: a string describing the module

str: a string that describes the module

str: a string that describes the module

str: the string of the module

Box head forward function used in both training and testing time.

Run forward function and calculate loss for box head in training.

Filter images too small or without ground truths.

Filter images too small or without ground truths.

Compute guided anchoring targets. This function returns sampled anchors and gt bboxes directly rather than calculates regression targ

Compute area ratio of the gt mask inside the proposal and the gt mask of the corresponding instance.

Transform outputs for a single batch item into labeled boxes. Args: cls_scores (list[Tensor]): Box scores for a single scale leve

Transform outputs for a single batch item into bbox predictions. Args: cls_scores (list[Tensor]): Box scores for each scale level

Get points according to feature map sizes.

Compute regression, classification targets for anchors in a single image. Args: flat_anchors (Tensor): Multi-level anchor

Compute regression, classification targets for anchors in a single image. Args: flat_anchors (Tensor): Multi-level anchor

Compute regression and classification targets for a single image.

Get training target of MaskPointHead for each image.

Compute regression and classification targets for anchors in a single image. Args: flat_anchors (Tensor): Multi-level anc

Compute regression and classification targets for anchors in a single image. Most of the codes are the same with the base class

Initialize layers of the head.

Initialize layers of the head.

Initialize layers of the head.

Initialize layers of the head.

Initialize layers of the head.

Initialize layers of the head.

Initialize layers of the head.

Initialize layers of the head.

Initialize layers of the head.