Initialize a DetectionEval object. :param nusc: A NuScenes object. :param config: A DetectionConfig object. :param re

The `__init__` method of any subclass should also contain these arguments. Args: in_channels (int): out_chan

CrossEntropyLoss. Args: use_sigmoid (bool, optional): Whether the prediction uses sigmoid of softmax. Defaults to

Args: min_sizes: list of short-edge size to resize the image to max_size: maximum height or width of resized images

Args: backbone: either a backbone module or a mmdet config dict that defines a backbone. The backbone takes a 4D

NOTE: this interface is experimental. Args: num_keypoints (int): number of keypoints to predict loss_weight

NOTE: this interface is experimental. Args: loss_weight (float): multiplier of the loss vis_period (int): vi

Args: backbone: a backbone module, must follow detectron2's backbone interface proposal_generator: a module that gene

Args: center_sampling_radius: radius of the "center" of a groundtruth box, within which all anchor points are lab

NOTE: this interface is experimental. Args: input_shape: shapes (channels and stride) of the input features

NOTE: this interface is experimental. Args: backbone: a backbone module, must follow detectron2's backbone interface

NOTE: this interface is experimental. Args: in_features (list[str]): list of names of input features to use

Args: model, data_loader, optimizer: same as in :class:`SimpleTrainer`. grad_scaler: torch GradScaler to automaticall

The `__init__` method of any subclass should also contain these arguments. Args: in_channels (int): out_chan

Deformable convolution from :paper:`deformconv`. Arguments are similar to :class:`Conv2D`. Extra arguments: Args:

Creates the matcher Params: cost_class: This is the relative weight of the classification error in the matching cost c

Add from_instances methods to the scripted Instances class.

Affine transform bboxes to input image. Args: results (dict): Result dict from loading pipeline. matrix (np.ndarray):

Assert that each stride is 2x times its preceding stride, i.e. "contiguous in log2".

Assert that each stride is 2x times its preceding stride, i.e. "contiguous in log2".

Assert that each stride is 2x times its preceding stride, i.e. "contiguous in log2".

Assign and sample proposals for training. Args: proposal_list (list[dict]): Proposals produced by RPN. gt_bboxes_3d (

Assign and sample proposals for training. Args: proposal_list (list[dict]): Proposals produced by RPN. gt_bboxes_3d (

ONNX exported network doesn't have concept of device, assign necessary device option for each op in order to make it runable on GPU runtime.

For each untracked instance, assign a new id Args: instances: D2 Instances, for predictions of the current frame

Run forward function and calculate loss for auxiliary head in training.

Forward training function of roi_extractor and bbox_head. Args: seg_feats (torch.Tensor): Point-wise semantic features.

Forward training function of roi_extractor and bbox_head. Args: features (torch.Tensor): Backbone features with depth and \

Run forward function and calculate loss for box head in training.

bbox post-processing method. The boxes would be rescaled to the original image scale and do the nms operation. Usually `with_nms` is

Build the default pipeline for this dataset.

Build the default pipeline for this dataset.

Build the default pipeline for this dataset.

Initialize predictor layers of a single level head.

Make ann_files as list/tuple.

Check if rotation matrix is valid for self.rotation_axis. Args: rot_mat (np.ndarray): Rotation matrix to be applied.

Make scene_idxs as list/tuple.

Checkpointining without re-entrant autograd Args: function: describes what to run in the forward pass of the model or part of

Configurations for some libraries.

Convert different format of boxes to an NxB array, where B = 4 or 5 is the box dimension.

Convert different format of masks or polygons to a tuple of masks and polygons. Returns: list[GenericMask]: