KittiDataLoader<T>
Models & Types · AiDotNet.Data.Geometry
Loads the KITTI 3D object detection dataset (LiDAR point clouds with 3D bounding boxes).
Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → KittiDataLoader<T>
How It Works
KITTI expects:
Features are point cloud Tensor[N, PointsPerSample * Channels]. Labels are the dominant object class per frame Tensor[N, 1] (0=Car, 1=Van, 2=Truck, 3=Pedestrian, 4=Person_sitting, 5=Cyclist, 6=Tram, 7=Misc).
Constructors
| Constructor | Summary |
|---|---|
KittiDataLoader(KittiDataLoaderOptions options) |
Properties
| Property | Summary |
|---|---|
int FeatureCount { get; } |
|
int OutputDimension { get; } |
|
int TotalCount { get; } |
|
string Description { get; } |
|
string Name { get; } |
Methods
| Method | Summary |
|---|---|
ValueTuple<IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>> Split(double trainRatio, double validationRatio, int? seed) |