Args: predictions: return values of :meth:`forward()`. proposals (list[Instances]): proposals that match the features

Dump an "Instances" object to a COCO-format json that's used for evaluation. Args: instances (Instances): img_id (int): the

Bilinear interpolation method to be used for upscaling Args: tensor_nchw (tensor): tensor of shape (N, C, H, W)

The inverse is to rotate it back with expand, and crop to get the original shape.

Returns whether execution is currently in Torch FX tracing mode

Similar to :meth:`latest`, but the returned values are either the un-smoothed original latest value, or a median of the given

List all registered datasets. Returns: list[str]

Load data from a file Args: fpath (str): file path to load data from

Load data from a file Args: fpath (str): file path to load data from

Args: image_dir (str): path to the raw dataset. e.g., "~/cityscapes/leftImg8bit/train". gt_dir (str): path to the raw annotations

Args: image_dir (str): path to the raw dataset. e.g., "~/cityscapes/leftImg8bit/train". gt_dir (str): path to the raw annotations

Loads a JSON file with annotations in COCO instances format. Replaces `detectron2.data.datasets.coco.load_coco_json` to handle metadata i

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

Load a json file in LVIS's annotation format. Args: json_file (str): full path to the LVIS json annotation file. image_root

Load precomputed object proposals into the dataset. The proposal file should be a pickled dict with the following keys: - "ids": list[i

Created list of ResNet stages from pre-defined depth (one of 18, 34, 50, 101, 152). If it doesn't create the ResNet variant you need,

Makes a donut shaped binary mask.

Compute the mask prediction loss defined in the Mask R-CNN paper. Args: pred_mask_logits (Tensor): A tensor of shape (B, C, Hmask, W

Merge detection results from different branches of TridentNet. Return detection results by applying non-maximum suppression (NMS) on bounding

Returns: (H, W) array, a mask for all pixels that have a prediction

Restrict angles to the range of [-180, 180) degrees

Pack data into tensors

Given two lists of boxes of size N and M, compute the intersection area between __all__ N x M pairs of boxes. The box order must be (xmin

recursively (post-order) update all modules with the target type and its subclasses, make a initialization/composition/inheritance/... via th

Get features from feature maps in `features_list` that correspond to specific point coordinates inside each bounding box from `boxes`.

Args: dataset_dicts (list[dict]): list of dataset dicts. class_names (list[str]): list of class names (zero-indexed).

Process the pair of inputs and outputs. If they contain batches, the pairs can be consumed one-by-one using `zip`: .. code-b

Register `symbolic_fn` as PyTorch's symbolic `opname`-`opset_version` for ONNX export. The registration is performed only when current PyTorc

Resample coarse segmentation tensor to the given bounding box and derive labels for each pixel of the bounding box Args: coarse_

Resample fine and coarse segmentation tensors to the given bounding box and derive labels for each pixel of the bounding box Args:

Resamples U and V coordinate estimates for the given bounding box Args: u (tensor [1, C, H, W] of float): U coordinates v (t

Resamples U and V coordinate estimates for the given bounding box Args: predictor_output (DensePoseChartPredictorOutput): DensePose

Visualizes predictions on frames of the input video. Args: video (cv2.VideoCapture): a :class:`VideoCapture` object, who

Sample point labels from ground truth mask given point_coords. Args: instances (list[Instances]): A list of N Instances, where N is

Args: filepath (str): a string that contains the absolute path, including the file name, where the visualized ima

Save the graph as SVG format. Args: output_file (str): a SVG file inputs: optional inputs given to the model

Save the model as caffe2's protobuf format. It saves the following files: * "model.pb": definition of the graph. Can be

Scale the box with horizontal and vertical scaling factors

Create configs and perform basic setups.

Return `num_samples` (or fewer, if not enough found) random samples from `labels` which is a mixture of positives & negatives. It will tr

Compute and display summary metrics for evaluation results. Note this function can *only* be applied on the default parameter setting

Helper function to synchronize (barrier) among all processes when using distributed training

Args: see documentation of :func:`paste_masks_in_image`.

Convert InstancesList to List[Instances]. The input `instances_list` can also be a List[Instances], in this case this method is a non

Unregister PyTorch's symbolic `opname`-`opset_version` for ONNX export. The un-registration is performed only when PyTorch's version is < `mi

Upgrade a config from its current version to a newer version. Args: cfg (CfgNode): to_version (int): defaults to the latest

Window unpartition into original sequences and removing padding. Args: x (tensor): input tokens with [B * num_windows, window_size, w

Args: loss_dict (dict): dict of scalar losses data_time (float): time taken by the dataloader iteration p

Helper function to Accumulate() Considers the evaluation results applicable to a particular category, area range, and max_detections parameter setting

Helper function to Accumulate() Compute a precision recall curve given a sorted list of detected instances encoded in evaluations, evaluation_indices,

For each IOU threshold, greedily match each detected instance to a ground truth instance (if possible) and store the results

Sort detections from highest score to lowest, such that detection_instances[detection_sorted_indices[t]] >= detection_instances[detection_sorted_indic

Partition the ground truth objects based on whether or not to ignore them based on area