Randomly modifies given color to produce a slightly different color than the color given. Args: color (tuple[double]): a

RoiAlignRotated with scale 1.0 and 0 sample ratio.

Transpose the dense per-level predictions. Args: predictions: a list of outputs, each is a list of per-level

Accumulate per image evaluation results and store the result in self.eval. Does not support changing parameter settings from those u

Benchmark the dataloader in each distributed worker, and log results of all workers. This helps understand the final performance as w

Built an anchor generator from `cfg.MODEL.ANCHOR_GENERATOR.NAME`.

Build a LR scheduler from config.

Clip (in place) the boxes by limiting x coordinates to the range [0, width] and y coordinates to the range [0, height]. For

Convert a scripted Instances object to a regular :class:`Instances` object

Create a small table using the keys of small_dict as headers. This is only suitable for small dictionaries. Args: small_dict (di

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

Args: x_data (list[int]): a list containing x values of all the points being drawn. Length of list should match t

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

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

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 :func:`fvcore.nn.flop_count` and adds supports for standard detec

Args: input: NCHW images rois: Bx5 boxes. First column is the index into N. The other 4 columns are xyxy.

A context manager that annotates the "training" attribute of every submodule to constant, so that the training codepath in these modules can

Get box regression transformation deltas (dx, dy, dw, dh) that can be used to transform the `src_boxes` into the `target_boxes`. That

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

Args: tensor (bool): if True, returns 3xHxW tensor. else, returns a HxWx3 numpy array. Returns: an image, in BGR

Returns: HistoryBuffer: the scalar history for name

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

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

Create a list of blocks of the same type that forms one ResNet stage. Args: block_class (type): a subclass of CNNBlockBa

Compare the "keep" result of two nms call. They are allowed to be different in terms of edit distance due to floating point precision iss

Paste a set of masks that are of a fixed resolution (e.g., 28 x 28) into an image. The location, height, and width for pasting each mask is d

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

Register a dataset in COCO's json annotation format for instance detection, instance segmentation and keypoint detection. (i.e., Type 1 a

Register a new conversation template.

Run :func:`torch.jit.script` on a model that uses the :class:`Instances` class. Since attributes of :class:`Instances` are "dynamically" adde

Check that the model must be called with the given input/output dtype

Args: optimizer, last_iter: See ``torch.optim.lr_scheduler._LRScheduler``. ``last_iter`` is the same as ``last_ep

Args: bottom_up (Backbone): module representing the bottom up subnetwork. Must be a subclass of :class:`Backbone`

Derive the desired score numbers from summarized COCOeval. Args: coco_eval (None or COCOEval): None represents no predic

Returns: str: module name of the caller tuple: a hashable key to be used to identify different callers

Internal function used to log the usage of different detectron2 components inside facebook's infra.

Log the classification metrics to EventStorage. Args: pred_logits: Rx(K+1) logits. The last column is for background class.

Rescale the output instances to the target size.

Uniform float random number between low and high.

In given proto, rename all blobs with matched version

mmdet will assert the type of dict/list. So convert omegaconf objects to dict/list.

Try select keys from cfg until the first key that exists. Otherwise return default.

Call `add_ground_truth_to_proposals_single_image` for all images. Args: gt(Union[List[Instances], List[Boxes]): list of N elements.

Run all_gather on arbitrary picklable data (not necessarily tensors). Args: data: any picklable object group: a torch proces

Applies Rotary Position Embedding to the query and key tensors. Args: q (`torch.Tensor`): The query tensor. k (`torch.Tensor`): T

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

When the config is defined for certain number of workers (according to ``cfg.SOLVER.REFERENCE_WORLD_SIZE``) that's different from the

Performs non-maximum suppression in a batched fashion. Each index value correspond to a category, and NMS will not be applied between el

Build a box head defined by `cfg.MODEL.ROI_BOX_HEAD.NAME`.

See get_caffe2_inputs() below.

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

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

Crop each bitmask by the given box, and resize results to (mask_size, mask_size). This can be used to prepare training targets for Ma