Converting the points set into bounding box. :param pts: the input points sets (fields), each points set (fields) is represented

Refine bboxes during training. Args: rois (Tensor): Shape (n*bs, 5), where n is image number per GPU, and bs is t

Dump the detection results to a COCO style json file. There are 3 types of results: proposals, bbox predictions, mask predictions, an

Show RPN proposals on the image. Although we assume batch size is 1, this method supports arbitrary batch size.

Wrap the FP32 model to FP16. 1. Convert FP32 model to FP16. 2. Remain some necessary layers to be FP32, e.g., normalization layers. Args

Convert ``xyxy`` style bounding boxes to ``xywh`` style for COCO evaluation. Args: bbox (numpy.ndarray): The bounding box

Add shared or separable branch. convs -> avg pool (optional) -> fcs

Create sample results that can be passed to BBoxHead.get_targets.

Gather feature according to index. Args: feat (Tensor): Target feature map. ind (Tensor): Target coord index.

Mask head forward function used in both training and testing.

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

Assign w.r.t. the overlaps of bboxes with gts. Args: overlaps (Tensor): Overlaps between k gt_bboxes and n bboxes,

Async inference image(s) with the detector. Args: model (nn.Module): The loaded detector. imgs (str/ndarray or list[str/ndarray])

Map bboxes from testing scale to original image scale.

Build neck.

Classification-Aware Regression Loss (CARL). Args: cls_score (Tensor): Predicted classification scores. labels (Tensor): Targets

Check if norm layer is in correct train state.

Async context manager that waits for work to complete on given CUDA streams.

see :func:`BaseInstanceMasks.crop`

See :func:`BaseInstanceMasks.crop_and_resize`.

Evaluate mAP of a dataset. Args: det_results (list[list]): [[cls1_det, cls2_det, ...], ...]. The outer list indicates images,

Calculate recalls. Args: gts (list[ndarray]): a list of arrays of shape (n, 4) proposals (list[ndarray]): a list of arrays of sha

Extract features. Args: img (torch.Tensor): Image tensor with shape (n, c, h ,w). Returns: list[torch.Tensor

Directly extract features from the backbone+neck.

Extract features from multiple images. Args: imgs (list[torch.Tensor]): A list of images. The images are augmente

see :func:`BaseInstanceMasks.flip`

Get category ids of repeat dataset by index. Args: idx (int): Index of data. Returns: list[int]: All categor

Chooses static padding if you have specified an image size, and dynamic padding otherwise. Static padding is necessary for ONNX exporting of

Importance-based Sample Reweighting (ISR_P), positive part. Args: cls_score (Tensor): Predicted classification scores. bbox_pred

make plugins for block. Args: in_channels (int): Input channels of plugin. plugins (list[dict]): List of plugins cfg

Make plugins for ResNet ``stage_idx`` th stage. Currently we support to insert ``context_block``, ``empirical_attention_block``, ``no

Merge augmented detection bboxes and scores. Args: aug_bboxes (list[Tensor]): shape (n, 4*#class) aug_scores (list[Tensor] or Non

nn.Module: normalization layer after the third convolution layer

See :func:`BaseInstanceMasks.rescale`.

Sample positive and negative bboxes. This is a simple implementation of bbox sampling given candidates, assigning results and ground

Expand an array of boxes by a given scale. Args: bboxes (Tensor): Shape (m, 4) scale (float): The scale factor of bboxes Ret

Test without augmentation. Args: x (tuple[Tensor]): Features from the upstream network, each is a 4D-tensor.

Convert tensor to images. Args: tensor (torch.Tensor): Tensor that contains multiple images mean (tuple[float], optional): Mean o

See :func:`BaseInstanceMasks.to_tensor`.

str: a "nice" summary string describing this module

Box head forward function used in both training and testing.

Validates model name.

Crop image with a given center and size, then paste the cropped image to a blank image with two centers align. This function is equiv

Check whether the center of each box is in the patch. Args: patch (list[int]): The cropped area, [left, top, right, bottom].

Get final border for the target size. This function generates a ``final_border`` according to image's shape. The area between ``final

Find the predefined detector config directory.

Sample fine grained feats from each level feature map and concatenate them together.

Estimate uncertainty based on pred logits. We estimate uncertainty as L1 distance between 0.0 and the logits prediction in 'mask_pred

Initialize classification conv layers of the head.

Initialize bbox regression conv layers of the head.

Extract local maximum pixel with given kernal. Args: heat (Tensor): Target heatmap. kernel (int): Kernel size of max

Mask refining process with point head in testing.

Generate mesh grid of x and y. Args: x (torch.Tensor): Grids of x dimension. y (torch.Tensor): Grids of y dimension.

Get top k positions from heatmap. Args: scores (Tensor): Target heatmap with shape [batch, num_classes, height, w

Add ground truth as assigned results. Args: gt_labels (torch.Tensor): Labels of gt boxes

Import a module from albumentations. It inherits some of :func:`build_from_cfg` logic. Args: cfg (dict): Config dict. It

Check if the weight(and bias) is all zero.

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

Flip bboxes horizontally or vertically. Args: bboxes (Tensor): Shape (..., 4*k) img_shape (tuple): Image shape. direction

Collect the information of the running environments.

Run code concurrently in different streams. :param streamqueue: asyncio.Queue instance. Queue tasks define the pool of streams used for conc

see :func:`BaseInstanceMasks.crop_and_resize`

Map EfficientNet model name to parameter coefficients.

Simple version of the ``kwarray.ensure_rng`` Args: rng (int | numpy.random.RandomState | None): if None, then defaults to the

Format the results to json (standard format for COCO evaluation). Args: results (list[tuple | numpy.ndarray]): Testing results of

Args: img (Tensor): Input images of shape (N, C, H, W). Typically these should be mean centered and std scaled.

Generate base anchors. Returns: list(torch.Tensor): Base anchors of a feature grid in multiple \ feature levels.

Generate 2D gaussian heatmap. Args: heatmap (Tensor): Input heatmap, the gaussian kernel will cover on it and maintain the ma

Base on the previous bboxes and regression values, we compute the regressed bboxes and generate the grids on the bboxes. :param reg:

Generate base anchors of a single level. Args: base_size (int | float): Basic size of an anchor. scales (torch.Tensor

Get squares according to feature map sizes and guided anchors. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes.

Get annotation by index. Args: idx (int): Index of data. Returns: dict: Annotation info of specified index.

Get COCO annotation by index. Args: idx (int): Index of data. Returns: dict: Annotation info of specified in