Add config for PointRend.

Match names between the two state-dict, and update the values of model_state_dict in-place with copies of the matched tensor in ckpt_state_di

A function to assemble caffe2 model's outputs (i.e. Dict[str, Tensor]) to detectron2's format (i.e. list of Instances instance). This onl

Build a LR scheduler from config.

Build a point head defined by `cfg.MODEL.POINT_HEAD.NAME`.

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

We estimate uncerainty as L1 distance between 0.0 and the logit prediction in 'logits' for the foreground class in `classes`. Args:

Remove all registered dataset.

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

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:

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

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

Draw panoptic prediction results on an image. Args: panoptic_seg (Tensor): of shape (height, width) where the values are

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

Run per image evaluation on given images and store results (a list of dict) in self.evalImgs :return: None

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

Export the model to ONNX format. Note that the exported model contains custom ops only available in caffe2, therefore it cann

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.

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

Flattens predictions in the batch

Flattens predictions in the batch

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

Calcute the confusion matrix by given label and pred :param gt_label: the ground truth label :param pred_label: the pred label :param

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

Returns: dict: a dict which maps names (str) to data of the fields Modifying the returned dict will modify this instance

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)

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

Find `num_points` most uncertain points from `uncertainty_map` grid. Args: uncertainty_map (Tensor): A tensor of shape (N, 1, H, W)

Sample points in [0, 1] x [0, 1] coordinate space based on their uncertainty. The unceratinties are calculated for each point using 'unce

Deprecated

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

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

Neural network layers that makes predictions from input features.

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

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

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

Binary Lovasz hinge loss logits: [P] Variable, logits at each prediction (between -\infty and +\infty) labels: [P] Tensor, binary gro

Multi-class Lovasz-Softmax loss probas: [P, C] Variable, class probabilities at each prediction (between 0 and 1) labels: [P] Tensor,

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

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

Coordinates transform that maps top left corner to (-1, -1) and bottom right corner to (1, 1). Used for torch.grid_sample to initialize the

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

transform bbox patch outputs to image output

Rearrange the tensor layout from the network output, i.e.: list[Tensor]: #lvl tensors of shape (N, A x K, Hi, Wi) to per-image prediction

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.

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