3D boxes of instances in LIDAR coordinates. Coordinates in LiDAR: .. code-block:: none up z x front (yaw

A wrapper around :class:`torch.nn.Conv2d` to support empty inputs and more features.

Compose multiple transforms sequentially. The pipeline registry of mmdet3d separates with mmdet, however, sometimes we may need to use mmdet's

expand + depthwise + pointwise

This structure stores a list of boxes as a Nx4 torch.Tensor. It supports some common methods about boxes (`area`, `clip`, `nonempty`, etc

This class represents a list of instances in an image. It stores the attributes of instances (e.g., boxes, masks, labels, scores) as "fields"

A simple structure that contains basic shape specification about a tensor. It is often used as the auxiliary inputs/outputs of models, to

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

r""" LayerNorm that supports two data formats: channels_last (default) or channels_first. The ordering of the dimensions in the inputs. channels_

A wrapper around :class:`torch.nn.Conv2d` to support empty inputs and more features.

This structure stores a list of rotated boxes as a Nx5 torch.Tensor. It supports some common methods about boxes (`area`, `clip`, `nonemp

NuScenesMap database class for querying and retrieving information from the semantic maps. Before using this class please use the provided tu

Implements feed-forward networks (FFNs) with residual connection. Args: embed_dims (int): The feature dimension. Same as `Mul

A warpper for torch.nn.MultiheadAttention. This module implements MultiheadAttention with residual connection, and positional encoding used i

3D boxes of instances in Depth coordinates. Coordinates in Depth: .. code-block:: none up z y front (yaw=-0.5*pi)

Region of interest feature map pooler that supports pooling from one or more feature maps.

Visualizer that draws data about detection/segmentation on images. It contains methods like `draw_{text,box,circle,line,binary_mask,polygon}

This class stores the segmentation masks for all objects in one image, in the form of bitmaps. Attributes: tensor: bool Tensor o

Same as :class:`Checkpointer`, but is able to: 1. handle models in detectron & detectron2 model zoo, and apply conversions for legacy models.

This stores a set of MetricData in a dict indexed by (name, match-distance).

Stores average precision and true positive metric results. Provides properties to summarize.

Data class that groups EvalBox instances by sample.

Absolute pos embedding, learned.

The box-to-box transform defined in R-CNN. The transformation is parameterized by 4 deltas: (dx, dy, dw, dh). The transformation scales the b

Multilayer perceptron.

3D boxes of instances in CAM coordinates. Coordinates in camera: .. code-block:: none z front (yaw=-0.5*pi)

Wrapper class to combine multiple :class:`DatasetEvaluator` instances. This class dispatches every evaluation call to all of its :class:

Data class used during detection evaluation. Can be a prediction or ground truth.

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Apply photometric distortion to image sequentially, every transformation is applied with a probability of 0.5. The position of random contrast is

Structure that holds a list of images (of possibly varying sizes) as a single tensor. This works by padding the images to the same size.

Position embedding with learnable embedding weights. Args: num_feats (int): The feature dimension for each position along x-ax

Args: c_dim (int): dimension of latent code c f_dim (int): feature dimension

A simple MLP module. Pass features (B, C, N) through an MLP. Args: in_channels (int, optional): Number of channels of input features

This class assigns to each predicted "element" (e.g., a box) a ground-truth element. Each predicted element will have exactly zero or one mat

r"""More general bbox head, with shared conv layers and two optional separated branches. .. code-block:: none /-> cls c

Two linear layers for predicting Fast R-CNN outputs: 1. proposal-to-detection box regression deltas 2. classification scores

Attribute: polygons (list[ndarray]): list[ndarray]: polygons for this mask. Each ndarray has format [x, y, x, y, ...]

Stores keypoint **annotation** data. GT Instances have a `gt_keypoints` property containing the x,y location and visibility flag of each keyp

r""" LayerNorm that supports two data formats: channels_last (default) or channels_first. The ordering of the dimensions in the inputs. channels_

Very simple multi-layer perceptron (also called FFN)

Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`Phi3DecoderLayer`] Args: config: Phi3Config

Point feature propagation module used in PointNets. Propagate the features from one set to another. Args: mlp_channels (list[int]):

Represent masks by N smaller masks defined in some ROIs. Once ROI boxes are given, full-image bitmask can be obtained by "pasting" the mask o

Points of instances in LIDAR coordinates. Args: tensor (torch.Tensor | np.ndarray | list): a N x points_dim matrix. points_dim (i

3d residual block for ImVoxelNeck. Args: n_channels (int): Input channels of a feature map.

ScanNet data. Generate scannet infos for scannet_converter. Args: root_path (str): Root path of the raw data. split (str, op

Tree in DLANet. Args: levels (int): The level of the tree. block (nn.Module): The block module in tree. in_channels: Inpu

Adaptive Mixing

Applies padding to input (if needed) so that input can get fully covered by filter you specified. It support two modes "same" and "corner". The

The box-to-box transform defined in Rotated R-CNN. The transformation is parameterized by 5 deltas: (dx, dy, dw, dh, da). The transformation

Similar to nn.ParameterList, but for buffers

A wrapper of class sampled dataset with ann_file path. Implementation of paper `Class-balanced Grouping and Sampling for Point Cloud 3D Object

Representing a list of detectron2.structures.Boxes from minibatch, each box is represented by a 5d vector (batch index + 4 coordinates), or a

A wrapper around the traced model in Caffe2's protobuf format. The exported graph has different inputs/outputs from the original Pytorch