Class PointNetPlusPlus<T>
- Namespace
- AiDotNet.PointCloud.Models
- Assembly
- AiDotNet.dll
Implements the PointNet++ architecture for hierarchical point cloud processing.
public class PointNetPlusPlus<T> : NeuralNetworkBase<T>, INeuralNetworkModel<T>, IInterpretableModel<T>, IInputGradientComputable<T>, IDisposable, IPointCloudClassification<T>, IPointCloudSegmentation<T>, IPointCloudModel<T>, INeuralNetwork<T>, IFullModel<T, Tensor<T>, Tensor<T>>, IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>, IModelSerializer, ICheckpointableModel, IParameterizable<T, Tensor<T>, Tensor<T>>, IFeatureAware, IFeatureImportance<T>, ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>, IGradientComputable<T, Tensor<T>, Tensor<T>>, IJitCompilable<T>Type Parameters
TThe numeric type used for calculations (e.g., float, double).
- Inheritance
-
PointNetPlusPlus<T>
- Implements
- Inherited Members
- Extension Methods
Remarks
For Beginners: PointNet++ extends PointNet by adding hierarchical feature learning at multiple scales.
Key improvements over PointNet: - Hierarchical structure: Processes point clouds at multiple resolutions - Local context: Captures fine-grained local patterns - Multi-scale grouping: Learns features at different scales simultaneously - Better generalization: More robust to non-uniform point density
Architecture components: 1. Set Abstraction Layers: Hierarchically group points and extract features - Sampling: Select subset of points as centroids - Grouping: Find neighboring points around each centroid - PointNet layer: Extract features from each local region 2. Feature Propagation Layers: Upsample features for segmentation tasks - Interpolation: Propagate features from coarse to fine levels - Skip connections: Combine with features from encoder
Why hierarchical learning matters: - Different patterns exist at different scales (like edges vs. shapes in images) - Local context provides detailed geometry information - Global context provides overall shape understanding - Combining both gives comprehensive understanding
Applications: - Fine-grained classification - Part segmentation (identifying specific parts of objects) - Semantic segmentation (labeling each point) - Better performance on complex, detailed shapes
Example use case - autonomous driving: - Coarse level: Identify general object shapes (car, pedestrian) - Medium level: Recognize object parts (wheels, windows) - Fine level: Detect details (door handles, mirrors)
Reference: "PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space" by Qi et al., NeurIPS 2017
Constructors
PointNetPlusPlus()
Initializes a new instance of the PointNetPlusPlus class with default options.
public PointNetPlusPlus()PointNetPlusPlus(PointNetPlusPlusOptions, ILossFunction<T>?)
Initializes a new instance of the PointNetPlusPlus class with configurable options.
public PointNetPlusPlus(PointNetPlusPlusOptions options, ILossFunction<T>? lossFunction = null)Parameters
optionsPointNetPlusPlusOptionsConfiguration options for the PointNet++ model.
lossFunctionILossFunction<T>Optional loss function for training.
PointNetPlusPlus(int, int[], double[], int[][], bool, ILossFunction<T>?)
Initializes a new instance of the PointNetPlusPlus class.
public PointNetPlusPlus(int numClasses, int[] samplingRates, double[] searchRadii, int[][] mlpDimensions, bool useMultiScaleGrouping = false, ILossFunction<T>? lossFunction = null)Parameters
numClassesintNumber of output classes.
samplingRatesint[]Number of points to sample at each hierarchy level.
searchRadiidouble[]Search radius for finding neighbors at each level.
mlpDimensionsint[][]MLP layer dimensions for each set abstraction level.
useMultiScaleGroupingboolWhether to use multi-scale grouping (MSG).
lossFunctionILossFunction<T>Optional loss function for training.
Remarks
For Beginners: Creates a PointNet++ model with hierarchical feature learning.
Parameters explained:
- numClasses: How many categories to classify into
- samplingRates: How many points to keep at each level
Example: [512, 128, 32] means:
- Level 1: Sample 512 points from input
- Level 2: Sample 128 points from the 512
- Level 3: Sample 32 points from the 128
- searchRadii: How far to look for neighbors at each level
Example: [0.1, 0.2, 0.4] means:
- Level 1: Look 0.1 units around each point
- Level 2: Look 0.2 units (larger neighborhood)
- Level 3: Look 0.4 units (even larger)
- mlpDimensions: Feature dimensions for processing at each level Example: [[64,64,128], [128,128,256], [256,512,1024]]
- useMultiScaleGrouping: Process each level at multiple scales (more robust but slower)
Example configuration for ModelNet40:
- samplingRates: [512, 128, null] (null means use all remaining points)
- searchRadii: [0.2, 0.4, null]
- mlpDimensions: [[64,64,128], [128,128,256], [256,512,1024]]
Properties
SupportsTraining
Indicates whether this network supports training (learning from data).
public override bool SupportsTraining { get; }Property Value
Remarks
For Beginners: Not all neural networks can learn. Some are designed only for making predictions with pre-set parameters. This property tells you if the network can learn from data.
Methods
Backpropagate(Tensor<T>)
Performs backpropagation to compute gradients for network parameters.
public override Tensor<T> Backpropagate(Tensor<T> outputGradient)Parameters
outputGradientTensor<T>
Returns
- Tensor<T>
The gradients of the loss with respect to the network inputs.
Remarks
For Beginners: Backpropagation is how neural networks learn. After making a prediction, the network calculates how wrong it was (the error). Then it works backward through the layers to figure out how each parameter contributed to that error. This method handles that backward flow of information.
The "gradients" are numbers that tell us how to adjust each parameter to reduce the error.
API Change Note: The signature changed from Vector<T> to Tensor<T> to support multi-dimensional gradients. This is a breaking change. If you need backward compatibility, consider adding an overload that accepts Vector<T> and converts it internally to Tensor<T>.
Exceptions
- InvalidOperationException
Thrown when the network is not in training mode or doesn't support training.
ClassifyPointCloud(Tensor<T>)
Classifies a point cloud into one of the predefined categories.
public Vector<T> ClassifyPointCloud(Tensor<T> pointCloud)Parameters
pointCloudTensor<T>Input point cloud tensor of shape [N, 3+F].
Returns
- Vector<T>
A vector of class probabilities of length C, where C is the number of classes.
Remarks
For Beginners: This method determines what object the point cloud represents.
The classification process:
- Takes the entire point cloud as input
- Processes all points together to understand the overall shape
- Returns probabilities for each possible category
Example with furniture classification:
- Input: Point cloud of a furniture piece
- Output: [0.85 chair, 0.10 stool, 0.03 table, 0.02 bench]
- The model predicts it's most likely a chair (85% confidence)
The returned probabilities sum to 1.0, allowing you to:
- Pick the most likely category (highest probability)
- Understand the model's confidence in its prediction
- Consider alternative possibilities if the top prediction has low confidence
CreateNewInstance()
Creates a new instance of the same type as this neural network.
protected override IFullModel<T, Tensor<T>, Tensor<T>> CreateNewInstance()Returns
- IFullModel<T, Tensor<T>, Tensor<T>>
A new instance of the same neural network type.
Remarks
For Beginners: This creates a blank version of the same type of neural network.
It's used internally by methods like DeepCopy and Clone to create the right type of network before copying the data into it.
DeserializeNetworkSpecificData(BinaryReader)
Deserializes network-specific data that was not covered by the general deserialization process.
protected override void DeserializeNetworkSpecificData(BinaryReader reader)Parameters
readerBinaryReaderThe BinaryReader to read the data from.
Remarks
This method is called at the end of the general deserialization process to allow derived classes to read any additional data specific to their implementation.
For Beginners: Continuing the suitcase analogy, this is like unpacking that special compartment. After the main deserialization method has unpacked the common items (layers, parameters), this method allows each specific type of neural network to unpack its own unique items that were stored during serialization.
ExtractGlobalFeatures(Tensor<T>)
Extracts global features from a point cloud.
public Vector<T> ExtractGlobalFeatures(Tensor<T> pointCloud)Parameters
pointCloudTensor<T>Input point cloud tensor of shape [N, 3+F] where N is number of points, and 3+F represents XYZ coordinates plus F additional features.
Returns
- Vector<T>
A feature vector representing the global characteristics of the point cloud.
Remarks
For Beginners: This method extracts a compact representation of the entire point cloud.
It's like creating a summary or "fingerprint" of the 3D object:
- Input: Many individual 3D points (could be thousands or millions)
- Output: A single feature vector that captures the essential characteristics
- This summary can be used for classification, detection, or comparison
For example, extracting global features from point clouds of chairs would produce similar feature vectors for all chairs, despite differences in specific details.
ExtractPointFeatures(Tensor<T>)
Extracts per-point features from a point cloud.
public Tensor<T> ExtractPointFeatures(Tensor<T> pointCloud)Parameters
pointCloudTensor<T>Input point cloud tensor of shape [N, 3+F].
Returns
- Tensor<T>
A tensor of shape [N, D] where D is the feature dimension for each point.
Remarks
For Beginners: This method extracts features for each individual point.
Unlike global features which summarize the entire cloud, per-point features describe each point:
- Input: N points with XYZ coordinates
- Output: N feature vectors, one for each point
- Each feature vector captures local and contextual information about that point
This is useful for tasks like:
- Point cloud segmentation (labeling each point)
- Finding specific features or parts in the 3D data
- Understanding the local geometry around each point
ForwardWithMemory(Tensor<T>)
Performs a forward pass through the network while storing intermediate values for backpropagation.
public override Tensor<T> ForwardWithMemory(Tensor<T> input)Parameters
inputTensor<T>The input data to the network.
Returns
- Tensor<T>
The output of the network.
Remarks
For Beginners: This method passes data through the network from input to output, but also remembers all the intermediate values. This is necessary for the learning process, as the network needs to know these values when figuring out how to improve.
API Change Note: The signature changed from Vector<T> to Tensor<T> to support multi-dimensional inputs. This is a breaking change. For backward compatibility, consider adding an overload that accepts Vector<T> and converts it internally to Tensor<T>.
Exceptions
- InvalidOperationException
Thrown when the network doesn't support training.
GetModelMetadata()
Gets the metadata for this neural network model.
public override ModelMetadata<T> GetModelMetadata()Returns
- ModelMetadata<T>
A ModelMetaData object containing information about the model.
InitializeLayers()
Initializes the layers of the neural network based on the architecture.
protected override void InitializeLayers()Remarks
For Beginners: This method sets up all the layers in your neural network according to the architecture you've defined. It's like assembling the parts of your network before you can use it.
Predict(Tensor<T>)
Makes a prediction using the neural network.
public override Tensor<T> Predict(Tensor<T> input)Parameters
inputTensor<T>The input data to process.
Returns
- Tensor<T>
The network's prediction.
Remarks
For Beginners: This is the main method you'll use to get results from your trained neural network. You provide some input data (like an image or text), and the network processes it through all its layers to produce an output (like a classification or prediction).
SegmentPointCloud(Tensor<T>)
Performs semantic segmentation on a point cloud.
public Tensor<T> SegmentPointCloud(Tensor<T> pointCloud)Parameters
pointCloudTensor<T>Input point cloud tensor of shape [N, 3+F].
Returns
- Tensor<T>
A tensor of shape [N, C] containing class probabilities for each point, where C is the number of classes.
Remarks
For Beginners: This method assigns a category label to each point.
For each point, it predicts which category it belongs to:
- Input: Point cloud with N points
- Output: For each point, probabilities for each possible category
- The category with highest probability is the predicted label
Example for indoor scene segmentation:
- Categories might be: floor, wall, ceiling, furniture, etc.
- Each point gets probabilities: [0.01 floor, 0.95 wall, 0.02 ceiling, 0.02 furniture]
- The point would be labeled as "wall" (highest probability)
SerializeNetworkSpecificData(BinaryWriter)
Serializes network-specific data that is not covered by the general serialization process.
protected override void SerializeNetworkSpecificData(BinaryWriter writer)Parameters
writerBinaryWriterThe BinaryWriter to write the data to.
Remarks
This method is called at the end of the general serialization process to allow derived classes to write any additional data specific to their implementation.
For Beginners: Think of this as packing a special compartment in your suitcase. While the main serialization method packs the common items (layers, parameters), this method allows each specific type of neural network to pack its own unique items that other networks might not have.
Train(Tensor<T>, Tensor<T>)
Trains the neural network on a single input-output pair.
public override void Train(Tensor<T> input, Tensor<T> expectedOutput)Parameters
inputTensor<T>The input data.
expectedOutputTensor<T>The expected output for the given input.
Remarks
This method performs one training step on the neural network using the provided input and expected output. It updates the network's parameters to reduce the error between the network's prediction and the expected output.
For Beginners: This is how your neural network learns. You provide: - An input (what the network should process) - The expected output (what the correct answer should be)
The network then:
- Makes a prediction based on the input
- Compares its prediction to the expected output
- Calculates how wrong it was (the loss)
- Adjusts its internal values to do better next time
After training, you can get the loss value using the GetLastLoss() method to see how well the network is learning.
UpdateParameters(Vector<T>)
Updates the network's parameters with new values.
public override void UpdateParameters(Vector<T> parameters)Parameters
parametersVector<T>The new parameter values to set.
Remarks
For Beginners: During training, a neural network's internal values (parameters) get adjusted to improve its performance. This method allows you to update all those values at once by providing a complete set of new parameters.
This is typically used by optimization algorithms that calculate better parameter values based on training data.