["abc.zfg", "abc.zef"] -> "abc."

Match proposals with groundtruth using the matcher at the given stage. Label the proposals as foreground or background based on the m

Args: features (list[Tensor]): #lvl input features to ROIHeads proposals (list[Instances]): #image Instances, with th

Based on the matching between N proposals and M groundtruth, sample the proposals and set their classification labels. Args:

Randomly sample a subset of positive and negative examples, and overwrite the label vector to the ignore value (-1) for all elements

Get COCO API "tasks" (i.e. iou_type) from COCO-format predictions.

Wrap Transform into Augmentation. Private, used internally to implement augmentations.

This function is used to transpose image first training targets to level first ones :return: level first training targets

Match names between the two state-dict, and returns a new chkpt_state_dict with names converted to match model_state_dict with heuristics. Th

Applies Rotary Position Embedding to the query and key tensors.

Inputs: boxes: n x 4 size_ranges: L x 2 Return: is_cared_in_the_level: n x L

Args: proposal_boxes/gt_boxes are tensors with the same shape (R, 4 or 5). pred_deltas has shape (R, 4 or 5), or (R,

Create a list of default :class:`Augmentation` from config. Now it includes resizing and flipping. Returns: list[Augmentation]

Create a list of default :class:`Augmentation` from config. Now it includes resizing and flipping. Returns: list[Augmentation]

Create evaluator(s) for a given dataset. This uses the special metadata "evaluator_type" associated with each builtin dataset. For your o

Build a mask head defined by `cfg.MODEL.ROI_MASK_HEAD.NAME`.

Returns: torch.nn.Module: It now calls :func:`detectron2.modeling.build_model`. Overwrite it if you'd like a dif

Create a Res2Net instance from config. Returns: ResNet: a :class:`ResNet` instance.

Build ROIHeads defined by `cfg.MODEL.ROI_HEADS.NAME`.

Build a semantic segmentation head from `cfg.MODEL.SEM_SEG_HEAD.NAME`.

Returns: iterable It now calls :func:`detectron2.data.build_detection_train_loader`. Overwrite it if you'd like

Calculate the instruction level accuracy for given Subject results

Args: instance_lists (list[Instances]) Returns: Instances

Convert an image from given format to RGB. Args: image (np.ndarray or Tensor): an HWC image format (str): the format of inpu

Resize the output instances. The input images are often resized when entering an object detector. As a result, we often need the outputs

Downgrade a config from its current version to an older version. Args: cfg (CfgNode): to_version (int): Note: A

Args: segment: numpy array of shape Nx2, containing all the points in the polygon. color: color of the polygon. Refer

Args: soft_mask (ndarray): float array of shape (H, W), each value in [0, 1]. color: color of the mask. Refer to `mat

Args: img_ids: a list of image IDs to evaluate on. Default to None for the whole dataset

Export the model to Caffe2's protobuf format. The returned object can be saved with its :meth:`.save_protobuf()` method. The

Export the model to a ``torch.jit.TracedModule`` by tracing. The returned object can be saved to a file by ``.save()``. Retu

Single-image inference. Return bounding-box detection results by thresholding on scores and applying non-maximum suppression (NMS). Args

Expand a hierarchical dict of scalars into a flat dict of scalars. If results[k1][k2][k3] = v, the returned dict will have the entry {"k1

Args: input: NCHW images rois: Bx6 boxes. First column is the index into N. The other 5 columns are (

Constructs a `Config` from a Python dictionary of parameters.

Returns the field called `name`.

Get question ids that satisfy given filter conditions. default skips that filter. :param imgIds (int array) : get question ids

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

Returns: The box centers in a Nx2 array of (x, y).