see :func:`BaseInstanceMasks.resize`

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

Box head forward function used in both training and testing.

Create sample results that can be passed to BBoxHead.get_targets.

Apply the target model to obtain the mask encodings

Calculate overlap between two set of bboxes. If ``is_aligned `` is ``False``, then calculate the overlaps between each bbox of bboxes1 and bb

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.

Concatenates two dicts without copying internal data.

See :func:`BaseInstanceMasks.crop`.

Get category ids of concatenated dataset by index. Args: idx (int): Index of data. Returns: list[int]: All c

Get the initial target model parameters given the few-shot labels

All inputs in original image coordinates. Generates a box in the cropped image sample reference frame, in the format used by the IoUNet.

All inputs in original image coordinates. Generates a box in the cropped image sample reference frame, in the format used by the IoUNet.

All inputs in original image coordinates. Generates a box in the cropped image sample reference frame, in the format used by the IoUNet.

Get parameters.

Loads a network checkpoint file. Can be called in three different ways: load_checkpoint(): Loads the latest epoch

In distributed setting, this function only download checkpoint at local rank 0.

nanmean compatible with generators.

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

Visualize the detection results on the image. Args: model (nn.Module): The loaded detector. img (str or np.ndarray): Image filena

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.

Box head forward function used in both training and testing.

Generates the gaussian label function centered at target_bb args: target_bboxes - target bounding box num_images*dict([4])

Mask head forward function used in both training and testing.

Samples num_ids frames between min_id and max_id for which target is visible args: visible - 1d Tensor indicating whether target

Get the flag indicate whether anchor centers are inside regions.

Map bboxes from testing scale to original image scale.

Build backbone.

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

Do inverse FFT corresponding to cfft2.

Calculates the intersection-over-union of two bounding boxes. Args: bbox1 (numpy.array, list of floats): bounding box in

See :func:`BaseInstanceMasks.crop_and_resize`.

Coerces input into a random number generator. If the input is None, then a global random state is returned. If the input is a numeric value,

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

Extract classification features based on the input backbone features.

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

see :func:`BaseInstanceMasks.flip`

Get a frame (image path) from client Returns: absolute path of the image

Get class names of a dataset.

Get the feature. Generally, call this function. args: im: image patch as a torch.Tensor.

Number of sequences in a dataset returns: int - number of sequences in the dataset.