Derive the desired score numbers from summarized COCOeval. Args: coco_eval (None or COCOEval): None represents no predic

Find proper places to draw text given a binary mask.

Apply EMA update to `self.name` using `value`. This is mainly used for loss normalizer. In Detectron1, loss is normalized by number

Extract arrays of I, U and V values at given points as numpy arrays given the data mode stored in self._dpDataMode

Forward logic of the box prediction branch. If `self.train_on_pred_boxes is True`, the function puts predicted boxes in the `prop

Args: features, targets: the same as in Same as in :meth:`ROIHeads.forward`. proposals (list[Instance

Forward logic of the densepose prediction branch. Args: features (dict[str, Tensor]): input data as a mapping from featu

Use `from_config` to obtain explicit arguments. Returns: dict: arguments to be used for cls.__init__

Produces embeddings and geodesic distance tensors for a given mesh. May subsample the mesh, if it contains too many vertices (control

Return a process group based on gloo backend, containing all the ranks The result is cached.

Return the learning rate warmup factor at a specific iteration. See :paper:`ImageNet in 1h` for more details. Args: method (str)

A context which ignores CUDA OOM exception from pytorch.

Computes utility values for linear interpolation at points v. The points are given as normalized offsets in the source interval (v0_src,

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

Prepare ._gts and ._dts for evaluation based on params :return: None

Abstract method to produce a sample of indices to select data To be implemented in descendants Args: values (tor

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

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

Open a context where some heads in `model.roi_heads` are temporarily turned off. Args: attr (list[str]): the attribute in

Accumulate per image evaluation results and store the result in self.eval. Does not support changing parameter settings from those u

Calculate decomposed Relative Positional Embeddings from :paper:`mvitv2`. https://github.com/facebookresearch/mvit/blob/19786631e330df9f3622e

Call `add_ground_truth_to_proposals_single_image` for all images. Args: gt(Union[List[Instances], List[Boxes]): list of N elements.

Called after the last iteration.

An FX-tracing safe version of assert. Avoids erroneous type assertion triggering when types are masked inside an fx.proxy.Proxy object during

Performs non-maximum suppression in a batched fashion. Each index value correspond to a category, and NMS will not be applied between el

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

Build a proposal generator from `cfg.MODEL.PROPOSAL_GENERATOR.NAME`. The name can be "PrecomputedProposals" to use no proposal generator.

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

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

equivalent to FastRCNNOutputLayers.inference

equivalent to mask_head.mask_rcnn_inference

Clip (in place) the boxes by limiting x coordinates to the range [0, width] and y coordinates to the range [0, height]. For

Load and prepare dataset dicts for training / testing Args: dataset_names (Collection[str]): a list of dataset names keep_in

3x3 convolution with padding

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

Convert a scripted Instances object to a regular :class:`Instances` object

When a dependency of a class is not available, create a dummy class which throws ImportError when used. Args: klass (str): name

When a dependency of a function is not available, create a dummy function which throws ImportError when used. Args: func (str):

Crop each bitmask by the given box, and resize results to (mask_size, mask_size). This can be used to prepare training targets for Ma

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

Draw semantic segmentation predictions/labels. Args: sem_seg (Tensor or ndarray): the segmentation of shape (H, W).

Evaluate/summarize the performance, after processing all input/output pairs. Returns: dict: A new evalua

Extract data for mask loss from instances that contain matched GT and estimated bounding boxes. Args: proposals_targets: Iterable