nn.Module: the normalization layer named "norm2"

nn.Module: normalization layer after the third convolution layer

Regress the bbox for the predicted class. Used in Cascade R-CNN. Args: rois (Tensor): Rois from `rpn_head` or last stage

Set user-defined new property.

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Tensor): Element-wise weights.

bbox post-processing method. The boxes would be rescaled to the original image scale and do the nms operation. Usually with_nms is Fa

Calculate overlap between two set of bboxes. FP16 Contributed by https://github.com/open-mmlab/mmdetection/pull/4889 Note: Assume bbo

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataload

Builder of IoU calculator.

Build neck.

Recursively convert Tensor in inputs from ``src_type`` to ``dst_type``. Args: inputs: Inputs that to be casted. src_type (torch.d

Multiple with alpha and add beat with clip.

Filter results using score threshold and topk candidates. Args: scores (Tensor): The scores, shape (num_bboxes, K). score_thr (fl

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

Forward function for plugins.

Args: imgs (List[Tensor]): the outer list indicates test-time augmentations and inner Tensor should have a shape

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

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

Parse the package dependencies listed in a requirements file but strips specific versioning information. Args: fname (str): path to r

Parse the package dependencies listed in a requirements file but strips specific versioning information. Args: fname (str): path to r

Show RPN proposals on the image. Args: data (str or np.ndarray): Image filename or loaded image. result (Tensor or tu

Simple forward test function.

Box head forward function used in both training and testing.

Box head forward function used in both training and testing.

Mask head forward function used in both training and testing.

Create a dummy onnx::NonMaxSuppression op while exporting to ONNX. This function helps exporting to onnx with batch and multiclass NMS op. It

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataload

Build projection layer for key/query/value/out.

Evaluate the dataset. Args: results (list[tuple[torch.Tensor]] | list[str]): per image pre_eval results or predi

Directly extract features from the backbone+neck.

Generate the coordinate. Args: featmap_sizes (tuple): The feature to be calculated, of shape (N, C, W, H). device (st

Get custom activation of cls_score. Args: cls_score (torch.Tensor): The prediction with shape (N, C + 2). Returns:

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

Make divisible function. This function rounds the channel number to the nearest value that can be divisible by the divisor. It is taken from

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

Prepare results dict for pipeline.

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

Convert objects of various python types to :obj:`torch.Tensor`. Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`, :class:`S

Box head forward function used in both training and testing.

A context which ignores CUDA OOM exception from pytorch. Code is modified from <https://github.com/facebookresearch/detectron2/blob/main/dete

Mask head forward function used in both training and testing.

Get the flag indicate whether anchor centers are inside regions.

Map bboxes from testing scale to original image scale.

Build linear layer. Args: cfg (None or dict): The linear layer config, which should contain: - type (str): Layer type.

Calculate region of the box defined by the ratio, the ratio is from the center of the box to every edge.

Calculate a proportional bbox region. The bbox center are fixed and the new h' and w' is h * ratio and w * ratio. Args: bbox (Tensor

Clip boxes dynamically for onnx. Since torch.clamp cannot have dynamic `min` and `max`, we scale the boxes by 1/max_shape and clamp in the

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

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

Calculate evaluation metrics Args: results (list[ndarray] | list[str]): List of prediction segmentation maps or list of predic

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

Get class weight for loss function. Args: class_weight (list[float] | str | None): If class_weight is a str, take it as a fil

Get user-defined property.

Get k of TopK for onnx exporting. The K of TopK in TensorRT should not be a Tensor, while in ONNX Runtime it could be a Tensor.Due to dynam

Load anns with the specified ids. self.anns is a list of annotation lists instead of a list of annotations. Args:

Make divisible function. This function rounds the channel number to the nearest value that can be divisible by the divisor. It is taken from

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

Apply same name function to all tensors in data_fields.

Convert [N, L, C] shape tensor to [N, C, H, W] shape tensor. Args: x (Tensor): The input tensor of shape [N, L, C] before conversion.

Convert [N, L, C] shape tensor to [N, C, H, W] shape tensor. Args: x (Tensor): The input tensor of shape [N, L, C] before conversion.

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

Prepare results dict for pipeline.

Get training data and annotations after pipeline. Args: idx (int): Index of data. Returns: dict: Training da

Prepare an example input image for ``generate_inputs_and_wrap_model``. Args: input_config (dict): customized config describing the exampl

Downsample the first feat and upsample last feat in feats.

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

Split side-aware features aligned with orders of bucketing targets.

Make sure different ranks share the same seed. All workers must call this function, otherwise it will deadlock. This method is generally used

Convert objects of various python types to :obj:`torch.Tensor`. Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`, :class:`S