Randomly sample a subset of positive and negative examples, and overwrite the label vector to the ignore value (-1) for all elements

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

Add config for DeepLab.

Call `add_ground_truth_to_proposals_single_image` for all images. Args: gt_boxes(list[Boxes]): list of N elements. Element i is a Bo

Add config for HRNet backbone.

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

Computes area of the mask. Only works with Polygons, using the shoelace formula: https://stackoverflow.com/questions/24467972

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 LR scheduler from config.

Build optimizer from configs. Args: model (:obj:`nn.Module`): The model with parameters to be optimized. optimizer_cfg (dict): Th

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

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

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:

Collect the information of the running environments.

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

3x3 convolution with padding

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

Decompresses DensePose chart-based result encoded into a base64 string Args: result (DensePoseChartResultCompressed): compressed Den

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

Dump IR of a TracedModule/ScriptModule at various levels. Useful for debugging. Args: model (TracedModule or ScriptModule): trac

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

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

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

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

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

Forward backbone. Args: img (Tensor): Input images of shape (N, C, H, W). Typically these should be mean centered

Forward backbone. Args: img (Tensor): Input images of shape (N, C, H, W). Typically these should be mean centered

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

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

Returns: dict[name -> HistoryBuffer]: the HistoryBuffer for all scalars

Deprecated

Initialize the weights of model. Args: pretrained (str, optional): Path to pre-trained weights. Default: None.

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

Log only for the first n times. Args: lvl (int): the logging level msg (str): n (int): name (str): name of t

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

If gradient clipping is enabled through config options, wraps the existing optimizer instance of some type OptimizerType to become an instanc

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

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

Normalize, pad and batch the input images.

Losses for segmentation and U/V coordinates computed as cross-entropy for segmentation unnormalized scores given ground truth labels

Fake losses for fine segmentation and U/V coordinates. These are used when no suitable ground truth data was found in a batch. The lo

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

Resample fine and coarse segmentation outputs from a predictor to the given bounding box and derive labels for each pixel of the bounding box