Get COCO category ids by index. Args: idx (int): Index of data. Returns: list[int]: All categories in the im

Get class names of a dataset.

Get user-defined property.

Compute corresponding GT box and classification targets for proposals. Args: proposals_list (list[list]): Multi level poi

Init module weights. We do nothing in this function because all modules we used (ConvModule, BasicBlock and etc.) have default initia

Are points located in bboxes. Args: points (Tensor): Points, shape: (m, 2). bboxes (Tensor): Bounding boxes, shape: (n, 4). Retu

Check if is one of the norms.

Compute loss of the head. Args: cls_scores (list[Tensor]): Box scores for each scale level Has shape (N, num_poin

Pack all blocks in a stage into a ``ResLayer``.

Dictionary mapper. Renames keys according to keymap provided. Args: d (dict): old dict keymap (dict): {'old_key':'new

Test model with multiple gpus. This method tests model with multiple gpus and collects the results under two different modes: gpu and cpu mod

nn.Module: normalization layer after the first convolution layer

nn.Module: normalization layer after the second convolution layer

Change from point offset to point coordinate.

padding has no effect on polygons`

Prepare results dict for pipeline.

Print time spent by CPU and GPU. Useful as a temporary context manager to find sweet spots of code suitable for async implementation.

calculate random scaling factor Args: s (float): range of the random scale. Returns: random scaling factor (float) whose

Simple version of ``kwimage.Boxes.random`` Returns: Tensor: shape (n, 4) in x1, y1, x2, y2 format. References: https://gitla

Randomly sample an img_scale when ``multiscale_mode=='range'``. Args: img_scales (list[tuple]): Images scale range for sampling.

see :func:`BaseInstanceMasks.rescale`

The forward function that also takes the RFP features as input.

Scale RoI coordinates by scale factor. Args: rois (torch.Tensor): RoI (Region of Interest), shape (n, 5) scale_factor

Set random seed. Args: seed (int): Seed to be used. deterministic (bool): Whether to set the deterministic option for

Test only det bboxes without augmentation.

Simple test for mask head without augmentation.

Smooth L1 loss. Args: pred (torch.Tensor): The prediction. target (torch.Tensor): The learning target of the prediction.

convert polygon masks to bitmap masks.

See :func:`BaseInstanceMasks.to_tensor`.

Bottleneck block for ResNeXt. If style is "pytorch", the stride-two layer is the 3x3 conv layer, if it is "caffe", the stride-two lay

str: the string of the module

Add the fc branch which consists of a sequential of conv layers.

Add default meta keys. We set default meta keys including `pad_shape`, `scale_factor` and `img_norm_cfg` to avoid the case where no `

Add the fc branch which consists of a sequential of fc layers.

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

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

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

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

Gets a block through a string notation of arguments.

Create random test data for the ``mmdet.models.bbox_heads.bbox_head.BBoxHead.refine_boxes`` method.

Convert detection results to COCO json style.

Paste instance masks acoording to boxes. This implementation is modified from https://github.com/facebookresearch/detectron2/ Args:

Encodes a block to a string.

Evaluation in Cityscapes protocol. Args: results (list): Testing results of the dataset. txtfile_prefix (str | None):

Filter images too small.

Transform outputs for a single batch item into bbox predictions. Args: cls_score_list (list[Tensor]): Box scores for a single sca