Change the device of the data inplace. Example: >>> self = SamplingResult.random() >>> print(f'self = {self.to(None)}

Convert targets by image to targets by feature level. [target_img0, target_img1] -> [target_level0, target_level1, ...]

Apply function to a list of arguments. Note: This function applies the ``func`` to multiple inputs and map the multiple outputs o

Unmap a subset of item (data) back to the original set of items (of size count)

Build loss.

Since teacher_model is registered as a plain object, it is necessary to put the teacher model to cuda when calling cuda function.

Decode the predicted bboxes according to prediction and base boxes.

See :func:`BaseInstanceMasks.expand`.

Convert a list of bboxes to roi format. Args: bbox_list (list[Tensor]): a list of bboxes corresponding to a batch of images.

Compute losses of the head. Args: cls_scores (list[Tensor]): Cls and quality scores for each scale level has shap

See :func:`BaseInstanceMasks.to_ndarray`.

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

:meth: read the object from a dict

Obtain the mean of tensor on different GPUs.

Assign gt to bboxes. The assignment is done in following steps 1. compute iou between all bbox (bbox of all pyramid levels) and gt

Generate grid anchors in multiple feature levels. Args: featmap_sizes (list[tuple]): List of feature map sizes in

Convert the model into training mode will keeping the normalization layer freezed.

Args: size (tuple): expected shape of dummy masks, (H, W) or (N, H, W) Return: ndarray: dummy mask

Build detector.

Decode distance prediction to bounding box. Args: points (Tensor): Shape (B, N, 2) or (N, 2). distance (Tensor): Distance from th

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

Calculate the ious between each bbox of bboxes1 and bboxes2. Args: bboxes1(ndarray): shape (n, 4) bboxes2(ndarray): shape (k, 4)

Args: size (tuple): expected shape of dummy masks, (N, H, W) Return: list[list[ndarray]]: dummy mask

See :func:`BaseInstanceMasks.flip`.

NMS for multi-class bboxes. Args: multi_bboxes (Tensor): shape (n, #class*4) or (n, 4) multi_scores (Tensor): shape (n, #class),

Validate the output of the onnxruntime backend is the same as the output generated by torch. Args: model (nn.Module | function): the

Builder of box assigner.

Builder of box sampler.

Build head.

Generate random bitmap masks for demo / testing purposes. Example: >>> from mmdet.core.mask.structures import BitmapMasks

Convert detection results to a list of numpy arrays. Args: bboxes (torch.Tensor | np.ndarray): shape (n, 5) labels (torch.Tensor

Encode deltas between bboxes and ground truth boxes.

Loss function of DIIHead, get loss of all images. Args: cls_score (Tensor): Classification prediction results of

Calculate accuracy according to the prediction and target. Args: pred (torch.Tensor): The model prediction, shape (N, num_class)

Get targets for PAA head. This method is almost the same as `AnchorHead.get_targets()`. We direct return the results from _get_target

Create a superset of inputs needed to run test or train batches. Args: input_shape (tuple): input batch dimensions n

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

Calculate the ground truth for all samples in a batch according to the sampling_results. Almost the same as the implementation in bbo

Check whether the anchors are inside the border. Args: flat_anchors (torch.Tensor): Flatten anchors, shape (n, 4). valid_flags (t

Check if is ResNet building block.

Parse the raw outputs (losses) of the network. Args: losses (dict): Raw output of the network, which usually contain

Get points according to feature map sizes. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes. img_meta

Get segmentation masks from mask_pred and bboxes. Args: mask_pred (Tensor or ndarray): shape (n, #class, h, w). F

Map bboxes from the original image scale to testing scale.

Builder of IoU calculator.

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

Concat multi-level feature maps by image. [feature_level0, feature_level1...] -> [feature_image0, feature_image1...] Convert the shape of eac

Grab configs necessary to create a detector. These are deep copied to allow for safe modification of parameters without influencing other tes

Initialize conv sequential for CornerHead.

Mask head forward function used in both training and testing.

Build distill loss.

Generate grid points of multiple feature levels. Args: featmap_sizes (list[tuple]): List of feature map sizes in

Random select some elements from the gallery. If `gallery` is a Tensor, the returned indices will be a Tensor; If `gallery` is a ndar

Replace the ImageToTensor transform in a data pipeline to DefaultFormatBundle, which is normally useful in batch inference. Args: pip

Convert masks to the format of ndarray.

Convert the model into training mode while keep normalization layer frozen.

Box forward function used in both training and testing.

Assign gt to bboxes. This method assign a gt bbox to every bbox (proposal/anchor), each bbox will be assigned with -1, or a semi-posi

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

Builder of box coder.

Build roi extractor.

Return the class containing the corresponding attributes according to the fpn_test_step_names.

Check if is one of the norms.

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

Generate sparse anchors according to the ``prior_idxs``. Args: prior_idxs (Tensor): The index of corresponding anchors

Transpose and gather feature according to index. Args: feat (Tensor): Target feature map. ind (Tensor): Target coord index.

Convert bbox coordinates from (cx, cy, w, h) to (x1, y1, x2, y2). Args: bbox (Tensor): Shape (n, 4) for bboxes. Returns: Ten

Convert bbox coordinates from (x1, y1, x2, y2) to (cx, cy, w, h). Args: bbox (Tensor): Shape (n, 4) for bboxes. Returns: Ten

Apply transformation `pred_bboxes` to `boxes`. Args: bboxes (torch.Tensor): Basic boxes. Shape (B, N, 4) or (N, 4) pr

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

Convert Mask to ndarray.. Args: mask (:obj:`BitmapMasks` or :obj:`PolygonMasks` or torch.Tensor or np.ndarray): The mask to be co

Merge augmented mask prediction. Args: aug_masks (list[ndarray]): shape (n, #class, h, w) img_shapes (list[ndarray]): shape (3, )

nn.Module: the normalization layer named "norm1"

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

Regress the bbox for the predicted class. Used in Cascade R-CNN. Args: rois (Tensor): shape (n, 4) or (n, 5) label (T

Set user-defined new property.

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