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

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

Build loss.

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

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

See :func:`BaseInstanceMasks.to_ndarray`.

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.

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

See :func:`BaseInstanceMasks.expand`.

Build detector.

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

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

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

Calculate accumulated score.

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.

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

Encode deltas between bboxes and ground truth boxes.

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

Initialize the weights of FPN module.

Build head.

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

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

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

Builder of box sampler.

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

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

Inference image(s) with the detector. Args: model (nn.Module): The loaded detector. imgs (str/ndarray or list[str/ndarray] or tup

See :func:`BaseInstanceMasks.flip`.

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)

Builder of box assigner.

Initialize a detector from config file. Args: config (str or :obj:`mmcv.Config`): Config file path or the config object.

Draw `result` on `img`. Args: img (str or tensor): The image to be displayed. result (dict): The results to draw on `

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

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

Load a text file and parse the content as a list of strings. The trailing "\\r" and "\\n" of each line will be removed. Note: This wi

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

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

dict: a dictionary of info about the object

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

Obtain the mean of tensor on different GPUs.

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

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.

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

Map bboxes from the original image scale to testing scale.

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

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

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.

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

See :func:`BaseInstanceMasks.rescale`.

See :func:`BaseInstanceMasks.resize`.

Convert masks to the format of ndarray.

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

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

Build roi extractor.

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

nn.Module: the normalization layer named "norm1"

Builder of box coder.

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

Generate char instance kernels for one shrink ratio. Args: resize_shape (tuple(int, int)): Image size (height, width)

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

Inference image(s) with the detector. Args: model (nn.Module): The loaded detector. imgs (str/ndarray or list[str/ndarray] or tup

Write a list of strings to a text file. Args: filename (str): The output filename. It will be created/overwritten. lines (list(st

See :func:`BaseInstanceMasks.pad`.

Convert strings to indexes. Args: strings (list[str]): ['hello', 'world']. Returns: indexes (list[list[int]])

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

Build a module. Args: cfg (dict, list[dict]): The config of modules, is is either a dict or a list of configs. regist

See :func:`BaseInstanceMasks.crop`.

Evaluation in hmean metric. Args: results (list[dict]): Each dict corresponds to one image, containing the following keys: bo

Extract features from images.

Generate effective mask by setting the ineffective regions to 0 and effective regions to 1. Args: mask_size (tuple): The

Compute the loss for text detection. Args: pred_maps (tensor): The input score maps of NxCxHxW. Returns: los

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, )

Parse the package dependencies listed in a requirements file but strip specific version information. Args: fname (str): Path to requi