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.

Build loss.

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

Apply same name function to all tensors in data_fields.

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

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

Decode the predicted bboxes according to prediction and base boxes.

See :func:`BaseInstanceMasks.expand`.

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

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

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

See :func:`BaseInstanceMasks.to_ndarray`.

Returns: list: Contains all keys in data_fields.

dict: a dictionary of info about the object

Returns: list: Contains all values in data_fields.

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

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

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

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

Build detector.

Build head.

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

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

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

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

Obtain the mean of tensor on different GPUs.

Builder of box assigner.

See :func:`BaseInstanceMasks.flip`.

Builder of box sampler.

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

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

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

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

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

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

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

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

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

Replace the string "${key}" with the corresponding value. Replace the "${key}" with the value of ori_cfg.key in the config. And support repla

Check whether the `pipeline_results` is the same with the predefined `results`. Args: results (dict): Predefined results which should

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

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

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

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

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

Check if is ResNet building block.

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

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

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

Add meta information. Args: meta_info (dict): A dict contains the meta information of image. such as `img_shape`,

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

Mask head 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

Map bboxes from the original image scale to testing scale.

Matrix NMS for multi-class masks. Args: masks (Tensor): Has shape (num_instances, h, w) labels (Tensor): Labels of corresponding

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.

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

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

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

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

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.

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

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

Builder of box coder.

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

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

Check if is one of the norms.

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

nn.Module: the normalization layer named "norm1"