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

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

Remove all registered dataset.

Implement a simple combining logic following "combine_semantic_and_instance_predictions.py" in panopticapi to produce panoptic segmentati

Convert BatchNorm/SyncBatchNorm in module into FrozenBatchNorm. Args: module (torch.nn.Module): Returns:

Converts dataset into COCO format and saves it to a json file. dataset_name must be registered in DatasetCatalog and in detectron2's standard

Perform some basic common setups at the beginning of a job, including: 1. Set up the detectron2 logger 2. Log basic information about en

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

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

Call `fast_rcnn_inference_single_image` for all images. Args: boxes (list[Tensor]): A list of Tensors of predicted class-specific or

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

Filter out images with too few number of keypoints. Args: dataset_dicts (list[dict]): annotations in Detectron2 Dataset format.

Implement operator-level flops counting using jit. This is a wrapper of fvcore.nn.flop_count, that supports standard detection models in

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

Args: image_size (tuple): height, width Returns: crop_size (tuple): height, width in absolute pixels

Load and prepare dataset dicts for instance detection/segmentation and semantic segmentation. Args: dataset_names (list[str]): a lis

Load LVIS metadata. Args: dataset_name (str): LVIS dataset name without the split name (e.g., "lvis_v0.5"). Returns: di

Like model_zoo.get, but do not load any weights (even pretrained)

Return the list of external input/output of sub-graph, each element is tuple of the name and corresponding version in predict_net. exter

Args: box_size (height, width): Size of the reference box. boundary_threshold (int): Boxes that extend beyond the ref

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

A wrapper around :func:`torch.nn.functional.interpolate` to support zero-size tensor.

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

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

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

Load semantic segmentation datasets. All files under "gt_root" with "gt_ext" extension are treated as ground truth annotations and all files

Args: For `gt_classes` and `gt_anchors_deltas` parameters, see :meth:`RetinaNet.get_ground_truth`. Th

Return the losses from a set of RPN predictions and their associated ground-truth. Returns: dict[loss name -> loss value

Create a resnet stage by creating many blocks. Args: block_class (class): a subclass of ResNetBlockBase num_blocks (int):

Convert pred_mask_logits to estimated foreground probability masks while also extracting only the masks for the predicted classes in pred_ins

Patching several inference functions inside ROIHeads and its subclasses Args: tensor_mode (bool): whether the inputs/out

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

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

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

Returns: list[Tensor]: A list of Tensors of predicted boxes for GT classes in case of class-specific box head. El

Return objectness logits in the same format as the proposals returned by :meth:`predict_proposals`. Returns: pre

Transform anchors into proposals by applying the predicted anchor deltas. Returns: proposals (list[Tensor]): A list of L

Normalize, pad and batch the input images.

Makes a function retry itself after encountering pytorch's CUDA OOM error. It will first retry after calling `torch.cuda.empty_cache()`.

Set the random seed for the RNG in torch, numpy and python. Args: seed (int): if None, will use a strong random seed.

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

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

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

Args: box2box_transform (Box2BoxTransform/Box2BoxTransformRotated): box2box transform instance for proposal-to-de

Args: src_rect (x0, y0, x1, y1): src coordinates output_size (h, w): dst image size interp: PIL interpola

Args: cfg (CfgNode):

Deformable convolution. Arguments are similar to :class:`Conv2D`. Extra arguments: Args: deformable_groups (int

Assert that each stride is 2x times its preceding stride, i.e. "contiguous in log2".

ONNX exported network doesn't have concept of device, assign necessary device option for each op in order to make it runable on GPU runtime.

Args: sizes (list[list[int]]): sizes[i] is the list of anchor sizes to use for the i-th feature map. If len(sizes

Configurations for some libraries.

Convert different format of boxes to an NxB array, where B = 4 or 5 is the box dimension.

Convert different format of masks or polygons to a tuple of masks and polygons. Returns: list[GenericMask]:

Args: boxes (list[Tensor]): per-image predicted boxes, each of shape Ri x 4 image_sizes (list[tuple]): list of image