Build a list of default hooks, including timing, evaluation, checkpointing, lr scheduling, precise BN, writing events. Retur

Constructs data loader based on inference results of a model.

Build a keypoint head from `cfg.MODEL.ROI_KEYPOINT_HEAD.NAME`.

Build a LR scheduler from config.

It now calls :func:`detectron2.solver.build_lr_scheduler`. Overwrite it if you'd like a different scheduler.

Build an optimizer from config.

Returns: torch.optim.Optimizer: It now calls :func:`detectron2.solver.build_optimizer`. Overwrite it if you'd li

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

Build an RPN head defined by `cfg.MODEL.RPN.HEAD_NAME`.

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

Build a list of writers to be used using :func:`default_writers()`. If you'd like a different list of writers, you can overwrite it i

Concatenates a list of RotatedBoxes into a single RotatedBoxes Arguments: boxes_list (list[RotatedBoxes]) Retur

Concatenates a list of BitMasks into a single BitMasks Arguments: bitmasks_list (list[BitMasks]) Returns:

Complete Intersection over Union Loss (Zhaohui Zheng et. al) https://arxiv.org/abs/1911.08287 Args: boxes1, boxes2 (Tensor): box

Delete all the stored histograms for visualization. This should be called after histograms are written to tensorboard.

Delete all the stored images for visualization. This should be called after images are written to tensorboard.

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

Construct the init_net from params dictionary

Convert DensePose predictor outputs to DensePoseResult using some registered converter. Does recursive lookup for base classes, so th

Convert DensePose predictor outputs to DensePoseResult with confidences using some registered converter. Does recursive lookup for ba

Convert PIL image to numpy array of target format. Args: image (PIL.Image): a PIL image format (str): the format of output i

Apply some basic name conversion to names in C2 weights. It only deals with typical backbone models. Args: original_keys (list[s

Convert all boxes in `box_lists` to the low-level format used by ROI pooling ops (see description under Returns). Args: box_list

Map Caffe2 Detectron weight names to Detectron2 names. Args: weights (dict): name -> tensor Returns: dict: detectron2 n

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

Convert an instance detection/segmentation or keypoint detection dataset in detectron2's standard format into COCO json format. Generic

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

Given a blob object, return the Caffe2 operator that creates this blob as constant. Currently support NumPy tensor and Caffe2 Int8Tensor.

Create a DistributedDataParallel model if there are >1 processes. Args: model: a torch.nn.Module fp16_compression: add fp16

Create an embedder based on the provided configuration Args: embedder_spec (CfgNode): embedder configuration embedder_dim (i

Create an extractor for the provided visualizer

Args: dataset_names: list of dataset names Returns: list[int]: a list of size=#keypoints, storing the horizontally-f

Args: instances: predictions from current frame prev_instances: predictions from previous frame iou_all: 2D numpy array c

Create a new output class from an existing one by adding new attributes related to confidence estimation: - coarse_segm_confidence (tenso

Create a new output class from an existing one by adding new attributes related to confidence estimation: - sigma_1 (tensor) - sigma_

Build a list of :class:`EventWriter` to be used. It now consists of a :class:`CommonMetricPrinter`, :class:`TensorboardXWriter` and :clas

Splits DensePose predictor outputs into chunks, each chunk corresponds to detections on one image. Predictor output chunks are stored in `pre

Distance Intersection over Union Loss (Zhaohui Zheng et. al) https://arxiv.org/abs/1911.08287 Args: boxes1, boxes2 (Tensor): box

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

Draws keypoints of an instance and follows the rules for keypoint connections to draw lines between appropriate keypoints. This follo

Args: box_coord (tuple): a tuple containing x0, y0, x1, y1 coordinates, where x0 and y0 are the coordinates of th

Args: circle_coord (list(int) or tuple(int)): contains the x and y coordinates of the center of the circle.

Draw panoptic prediction annotations or results. Args: panoptic_seg (Tensor): of shape (height, width) where the values

Draw a rotated box with label on its top-left corner. Args: rotated_box (tuple): a tuple containing (cnt_x, cnt_y, w, h,

Save extra metadata that will be used by inference in the output protobuf.

Convert semantic segmentation to COCO stuff format with segments encoded as RLEs. See http://cocodataset.org/#format-results

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

Export a caffe2-compatible Detectron2 model to caffe2 format via ONNX. Arg: model: a caffe2-compatible version of detectron2 model,

Trace and export a model to onnx format. Args: model (nn.Module): inputs (tuple[args]): the model will be called by `model(*

Fake segmentation loss used when no suitable ground truth data was found in a batch. The loss has a value 0 and is primarily used to

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

Single-image inference. Return rotated bounding-box detection results by thresholding on scores and applying rotated non-maximum suppression

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

Filter out images with none annotations or only crowd annotations (i.e., images without non-crowd annotations). A common training-time pr

For each feature map, select the `pre_nms_topk` highest scoring proposals, apply NMS, clip proposals, and remove small boxes. Return the `pos

For each feature map, select the `pre_nms_topk` highest scoring proposals, apply NMS, clip proposals, and remove small boxes. Return the `pos