Private function to load mask and semantic segmentation annotations. In gt_semantic_seg, the foreground label is from `0` to `num_thi

Private function to load semantic segmentation annotations. Args: results (dict): Result dict from :obj:`dataset`. Retur

Log the W&B Tables for validation data as artifact and calls `use_artifact` on it so that the evaluation table can use the reference o

use deconv layers to upsample backbone's output.

Args: cls_pred (Tensor): Predicted classfication logits in shape (num_query, d1, ..., dn), dtype=torch.float32.

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

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

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

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

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

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

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

Export mask refining process with point head to onnx. Args: x (tuple[Tensor]): Feature maps of all scale level. rois

MixUp transform function. Args: results (dict): Result dict. Returns: dict: Updated result dict.

Calculate global coordinate of mosaic image and local coordinate of cropped sub-image. Args: loc (str): Index for the sub

Mosaic transform function. Args: results (dict): Result dict. Returns: dict: Updated result dict.

Export the process of sampling fine grained feats to onnx. Args: x (tuple[Tensor]): Feature maps of all scale level.

Pad images according to ``self.size``.

Pad masks according to ``results['pad_shape']``.

Pad semantic segmentation map according to ``results['pad_shape']``.

Convert panoptic results to COCO panoptic json style.

Parse annotations and load panoptic ground truths. Args: img_info (int): Image info of an image. ann_info (list[dict]

Parse bbox and mask annotation. Args: ann_info (list[dict]): Annotation info of an image. with_mask (bool): Whether t

Private function to convert masks represented with polygon to bitmaps. Args: mask_ann (list | dict): Polygon mask annotat

Compute the area of a component of a polygon. Using the shoelace formula: https://stackoverflow.com/questions/24467972/calculate-area

Convert proposal results to COCO json style.

Get another random index from the same group as the given index.

Ramdom jitter positive proposals for training.

Resize bounding boxes with ``results['scale_factor']``.

Resize images with ``results['scale']``.

Resize masks with ``results['scale']``

Resize semantic segmentation map with ``results['scale']``.

Rotate the bboxes.

Rotate the image. Args: results (dict): Result dict from loading pipeline. angle (float): Rotation angle in degrees,

Rotate the masks.

Rotate the segmentation map.

Sample negative samples.

Sample negative samples. Score-HLR sampler is done in the following steps: 1. Take the maximum positive score prediction of each nega

Sample positive samples.

Randomly sample some positive samples.

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: module

Select some objects from the source results.

Set flag according to image aspect ratio. Images with aspect ratio greater than 1 will be set as group 1, otherwise group 0.

Merge thing classes to one class. In PanopticFPN, the background labels will be reset from `0` to `self.num_stuff_classes-1`, the for

Shear the bboxes.

Shear the image. Args: results (dict): Result dict from loading pipeline. magnitude (int | float): The magnitude used

Shear the masks.

Shear the segmentation maps.

Get features from pos rois.

Around padding the original image without cropping. The padding mode and value are from ``test_pad_mode``. Args: results

Random crop and around padding the original image. Args: results (dict): Image infomations in the augment pipeline. Retu

Shift bboxes horizontally or vertically, according to offset.

Translate the image. Args: results (dict): Result dict from loading pipeline. offset (int | float): The offset for tr

Translate masks horizontally or vertically.

Translate segmentation maps horizontally or vertically.

Update wandb config.

Add extra files that are required to support MIM into the package. These files will be added by creating a symlink to the originals if the pa

Add parent classes of the corresponding class of the ground truth bboxes.

Adjusts the compatibility of widths and groups. Args: widths (list[int]): Width of each stage. bottleneck_ratio (floa

Associative Embedding Loss in one image. Associative Embedding Loss including two parts: pull loss and push loss. Pull loss makes embedding v

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

Analyze detection results on each image. Args: confusion_matrix (ndarray): The confusion matrix, has shape (num_classes + 1,

Get anchor centers from anchors. Args: anchors (Tensor): Anchor list with shape (N, 4), "xyxy" format. Returns:

Assign only one gt index to each prior box. Gts with large gt_priority are more likely to be assigned. Args: is_bbox_in_

Extract direction-specific features fx and fy with attention methanism.

Test function with test time augmentation.

Test det bboxes with test time augmentation.

Test det bboxes with test-time augmentation. Args: feats (list[Tensor]): the outer list indicates test-time augmen

Automatically scaling LR according to GPU number and sample per GPU. Args: cfg (config): Training config. distributed (bool): Usi

Calculate average precision (for single or multiple scales). Args: recalls (ndarray): shape (num_scales, num_dets) or (num_dets, )

Calculate balanced L1 loss. Please see the `Libra R-CNN <https://arxiv.org/pdf/1904.02701.pdf>`_ Args: pred (torch.Tensor): The pred

Generate buckets estimation and fine regression targets. Args: proposals (Tensor): Shape (n, 4) gt (Tensor): Shape (n, 4)

Compute deltas of proposals w.r.t. gt. We usually compute the deltas of x, y, w, h of proposals w.r.t ground truth bboxes to get regression t