Convert pytorch-style structured inputs to caffe2-style inputs that are tuples of tensors. Args: batched_inputs

Returns the URL to the model trained using the given config Args: config_path (str): config file name relative to detectron2's "conf

Returns path to a builtin config file. Args: config_path (str): config file name relative to detectron2's "configs/" dir

Get all the configuration files (relative to the base configuration directory)

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

Create evaluator(s) for a given dataset. This uses the special metadata "evaluator_type" associated with each builtin dataset. For your o

Get all the evolution configuration files (relative to the base configuration directory)

Args: anchors (list[list[Boxes]]): a list of N=#image elements. Each is a list of #feature level Boxes. The Boxes

Get all the HRNet configuration files (relative to the base configuration directory)

Post-processing for instance segmentation, gets class agnostic instance id. Args: sem_seg: A Tensor of shape [1, H, W], predicted sem

Get the model from the specified file (relative to the base configuration directory)

Return a list of configs to include in package for model zoo. Copy over these configs inside detectron2/model_zoo.

Creates a function that converts outputs of the caffe2 model to detectron2's standard format. The function uses information i

Post-processing for panoptic segmentation. Args: sem_seg: A Tensor of shape [1, H, W] of predicted semantic label. center_hea

Take the output blobs from init_net by running it. Outputs: params: dict from blob name to numpy array device_options: dict f

Convert box-normalized [0, 1] x [0, 1] point cooordinates to image-level coordinates. Args: boxes_coords (Tensor): A tensor of shape

Get all the quick schedules configuration files (relative to the base configuration directory)

For ONNX exported model, GroupNorm will be represented as ATen op, this can be a drop in replacement from ATen to GroupNorm

Gives each pixel in the image an instance id. Args: center_points: A Tensor of shape [K, 2] where K is the number of center points.

Guess the version of a partial config where the VERSION field is not specified. Returns the version, or the latest if cannot make a guess.

Extract predicted keypoint locations from heatmaps. Args: maps (Tensor): (#ROIs, #keypoints, POOL_H, POOL_W). The predicted heatmap

Idenfity the reshape sub-graph in a protobuf. The reshape sub-graph is defined as matching the following pattern: (input_blob) -> Op_1 -

Crop split_per_side x split_per_side patches from input image. Args: img (PIL Image): input image. Returns: list[PIL Image]:

Run inference on the given inputs. Args: batched_inputs (list[dict]): same as in :meth:`forward` detected_in

A context where the model is temporarily changed to eval mode, and restored to previous mode afterwards. Args: model: a torch Mo

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

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

Initialize memory modules.

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

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

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

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

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

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

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

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

Args: box_size (height, width): Size of the reference box. boundary_threshold (int): Boxes that extend beyond the ref

Post process each predicted keypoint heatmap in `pred_keypoint_logits` into (x, y, score) and add it to the `pred_instances` as a `pred_k

Arguments: pred_keypoint_logits (Tensor): A tensor of shape (N, K, S, S) where N is the total number of instances in the batc

Args: anchors (list[Boxes]): A list of #feature level Boxes. The Boxes contains anchors of this image on the spec

Args: anchors (list[Boxes]): anchors for each feature map. gt_instances: the ground-truth instances for each image.

Returns: dict[str -> (float, int)]: mapping from the name of each scalar to the most recent value and the iterati

Neural network layers that makes predictions from regional input features.

Neural network layers that makes predictions from input features.

Args: dir (str): a directory used to save Caffe2Model with :meth:`save_protobuf`. The files "mode

Log no more than once per n seconds. Args: lvl (int): the logging level msg (str): n (int): name (str): name

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

Args: anchors (list[Boxes]): a list of #feature level Boxes gt_labels, gt_boxes: see output of :meth:`RetinaNet.label

Args: For `gt_class_info`, `gt_delta_info`, `gt_mask_info` and `num_fg` parameters, see :meth:`TensorMask.get_gro