Returns: HistoryBuffer: the scalar history for name

Run model on the data_loader and evaluate the metrics with evaluator. Also benchmark the inference speed of `model.forward` accurately. T

Prepare some proposals to be used to train the ROI heads. It performs box matching between `proposals` and `targets`, and assigns

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

Transpose/reshape a tensor from (N, (A x K), H, W) to (N, (HxWxA), K)

Returns: list[Tensor]: A list of Tensors of predicted class-specific or class-agnostic boxes for each image. Elem

Print main metrics in a format similar to Detectron, so that they are easy to copypaste into a spreadsheet. Args: results (Order

Register hooks to the trainer. The hooks are executed in the order they are registered. Args: hooks (list[Option

Preparation for a new round of evaluation. Should be called before starting a round of evaluation.

Compute and display summary metrics for evaluation results. Note this functin can *only* be applied on the default parameter setting

Args: cfg (CfgNode): torch_model (nn.Module): the detectron2 model (meta_arch) to be converted.

Caffe2 implementation of preprocess_image, which is called inside each MetaArch's forward. It normalizes the input images, and the fi

Args: classes (list[int] or None): scores (list[float] or None): class_names (list[str] or None): Returns: l

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

Forward logic of the keypoint prediction branch. Args: features (list[Tensor]): #level input features for keypoint predi

Forward logic of the mask prediction branch. Args: features (list[Tensor]): #level input features for mask prediction

Rescale the output instances to the target size.

In given proto, rename all blobs with matched version

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

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

Build a LR scheduler from config.

Check that the datasets have consistent metadata. Args: key (str): a metadata key dataset_names (list[str]): a list of datas

See get_caffe2_inputs() below.

Create a parser with some common arguments used by detectron2 users. Returns: argparse.ArgumentParser:

Args: binary_mask (ndarray): numpy array of shape (H, W), where H is the image height and W is the image width. E

Args: text (str): class label position (tuple): a tuple of the x and y coordinates to place text on image.

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

Use the given boxes in `instances` to produce other (non-box) per-ROI outputs. Args: features: same as in `forward()`

Return dict from versioned blob to list of (i, j), where i is index of consumer op, j is the index of input of that op.

like `get_fields` in the Instances object, but return each field in tensor representations

Return dict from versioned blob to (i, j), where i is index of producer op, j is the index of output of that op.

Return the device type ("cpu" or "gpu"/"cuda") of each (versioned) blob

Args: score_thresh (float): same as fast_rcnn_inference. nms_thresh (float): same as fast_rcnn_inference.

Args: main_func: a function that will be called by `main_func(*args)` num_machines (int): the total number of machines ma

Load a json file with COCO's instances annotation format. Currently supports instance detection, instance segmentation, and person keypoi

Returns: list[Tensor]: A list of Tensors of predicted class probabilities for each image. Element i has shape (Ri

Args: box_scores (N, 5): boxes in corner-form and probabilities. (Note here 5 == 4 + 1, i.e., 4-dim horizontal bo

Rename the op_id-th operator in predict_net, change it's output_id-th input's name to the new_name. It also does automatic re-route and c

Return semantic segmentation predictions in the original resolution. The input images are often resized when entering semantic segmentor. Mo

Args: cfg (CfgNode): model (nn.Module): evaluators (list[DatasetEvaluator] or None): if None, will call

Args: results (OrderedDict[dict]): task_name -> {metric -> score} Returns: bool: whether the verification succeeds or not

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

Naive tracking heuristics to assign same color to the same instance, will update the internal state of tracked instances. Re

Execute inference on a list of inputs, using batch size = self.batch_size, instead of the length of the list. Inputs & outpu

Calculate proper im2col step size, which should be divisible by input_size and not larger than prefer_size. Meanwhile the step size s

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

Forward logic of the mask prediction branch. Args: features (list[Tensor]): #level input features for mask prediction

Forward logic of the box prediction branch. If `self.train_on_pred_boxes is True`, the function puts predicted boxes in the `prop

Forward logic of the box prediction branch. If `self.train_on_pred_boxes is True`, the function puts predicted boxes in the `prop

Forward logic of the mask prediction branch. Args: features (list[Tensor]): #level input features for mask prediction

Return a process group based on gloo backend, containing all the ranks The result is cached.

Return the learning rate warmup factor at a specific iteration. See https://arxiv.org/abs/1706.02677 for more details. Args: met

A context which ignores CUDA OOM exception from pytorch.

Returns: list[int]: size of the tensor, on each rank Tensor: padded tensor that has the max size

Returns: Tensor: A Tensors of predicted class-specific or class-agnostic boxes for all images in a batch. Element

Based on the matching between N proposals and M groundtruth, sample the proposals and set their classification labels. Args:

Open a context where one head in `model.roi_heads` is temporarily turned off. Args: attr (str): the attribute in `model.r

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

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

Number of available virtual or physical CPUs on this system, i.e. user/real as output by time(1) when called with an optimally scaling usersp

Returns: DatasetEvaluator or None It is not implemented by default.

Build a mask head defined by `cfg.MODEL.ROI_MASK_HEAD.NAME`.

Returns: torch.nn.Module: It now calls :func:`detectron2.modeling.build_model`. Overwrite it if you'd like a dif

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_test_loader`. Overwrite it if you'd like a