Concat the predictions of all :obj:`InstanceData` in the list. Args: instances_list (list[:obj:`InstanceData`]): A list

Apply same name function to all tensors in data_fields.

Apply same name function to all tensors in data_fields.

Apply same name function to all tensors in data_fields.

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

Build loss.

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.

Apply same name function to all tensors in data_fields.

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

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

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

Build head.

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

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

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

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

Returns: list: Contains all keys in data_fields.

Obtain the mean of tensor on different GPUs.

dict: a dictionary of info about the object

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

Builder of box assigner.

Builder of box sampler.

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

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

Encode deltas between bboxes and ground truth boxes.

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

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

Returns: list: Contains all values in data_fields.

See :func:`BaseInstanceMasks.flip`.

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

Return a new results with same image meta information. Args: meta_info (dict, optional): A dict contains the meta information

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

Mask head forward function used in both training and testing.

Map bboxes from the original image scale to testing scale.

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

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

Initialize conv sequential for CornerHead.

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

Evaluate in VOC protocol. Args: results (list[list | tuple]): Testing results of the dataset. metric (str | list[str]

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

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

Update data root according to env MMDET_DATASETS. If set env MMDET_DATASETS, update cfg.data_root according to MMDET_DATASETS. Otherwise, usi

Box forward function used in both training and testing.

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

Builder of box coder.

Build detector.

nn.Module: the normalization layer named "norm1"

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

Build roi extractor.

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

Extract a multi-scale single image tensor from a multi-scale batch tensor based on batch index. Note: The default value of detach is True, be

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

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

Build backbone.

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.

Apply same name function to all tensors in data_fields.

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

Get root logger. Args: log_file (str, optional): File path of log. Defaults to None. log_level (int, optional): The level of logg

Draw bboxes and class labels (with scores) on an image. Args: img (str | ndarray): The image to be displayed. bboxes (ndarray): B

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

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

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.

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

Builder of IoU calculator.

Build neck.

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

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

See :func:`BaseInstanceMasks.pad`.

Prepare results dict for pipeline.

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

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

Directly extract features from the backbone+neck.

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