Table of Contents

Class FlowFormer<T>

Namespace
AiDotNet.Video.Motion
Assembly
AiDotNet.dll

FlowFormer: A Transformer Architecture for Optical Flow.

public class FlowFormer<T> : NeuralNetworkBase<T>, INeuralNetworkModel<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>, IInterpretableModel<T>, IInputGradientComputable<T>, IDisposable

Type Parameters

T

The numeric type used for calculations.

Inheritance
FlowFormer<T>
Implements
IFullModel<T, Tensor<T>, Tensor<T>>
IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>
IParameterizable<T, Tensor<T>, Tensor<T>>
ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>
IGradientComputable<T, Tensor<T>, Tensor<T>>
Inherited Members
Extension Methods

Remarks

For Beginners: FlowFormer estimates optical flow - the apparent motion of objects between consecutive video frames. Unlike traditional methods, it uses transformers to capture long-range dependencies in the cost volume.

Optical flow is useful for:

  • Video stabilization
  • Object tracking
  • Action recognition
  • Video editing and effects

Example usage:

var model = new FlowFormer<double>(arch);
var flow = model.EstimateFlow(frame1, frame2);
// flow[0] = horizontal motion, flow[1] = vertical motion

Technical Details: - Transformer-based cost volume aggregation - Latent cost tokens for efficient memory - Iterative flow refinement - State-of-the-art accuracy on Sintel and KITTI benchmarks

Reference: "FlowFormer: A Transformer Architecture for Optical Flow" ECCV 2022 https://arxiv.org/abs/2203.16194

Constructors

FlowFormer(NeuralNetworkArchitecture<T>, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>?, ILossFunction<T>?, int, int, int) 

public FlowFormer(NeuralNetworkArchitecture<T> architecture, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null, int embedDim = 256, int numLayers = 6, int numIterations = 12)

Parameters

architecture NeuralNetworkArchitecture<T>
optimizer IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>
lossFunction ILossFunction<T>
embedDim int
numLayers int
numIterations int

FlowFormer(NeuralNetworkArchitecture<T>, string) 

public FlowFormer(NeuralNetworkArchitecture<T> architecture, string onnxModelPath)

Parameters

architecture NeuralNetworkArchitecture<T>
onnxModelPath string

Properties

SupportsTraining

Indicates whether this network supports training (learning from data).

public override bool SupportsTraining { get; }

Property Value

bool

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

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

reader BinaryReader

The 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.

EstimateBidirectionalFlow(Tensor<T>, Tensor<T>)

Estimates bidirectional flow (forward and backward).

public (Tensor<T> Forward, Tensor<T> Backward) EstimateBidirectionalFlow(Tensor<T> frame1, Tensor<T> frame2)

Parameters

frame1 Tensor<T>
frame2 Tensor<T>

Returns

(Tensor<T> grad1, Tensor<T> grad2)

EstimateFlow(Tensor<T>, Tensor<T>)

Estimates optical flow between two frames.

public Tensor<T> EstimateFlow(Tensor<T> frame1, Tensor<T> frame2)

Parameters

frame1 Tensor<T>

First frame [B, C, H, W] or [C, H, W].

frame2 Tensor<T>

Second frame with same shape.

Returns

Tensor<T>

Flow tensor [B, 2, H, W] where channel 0 is horizontal and channel 1 is vertical flow.

EstimateFlowForVideo(List<Tensor<T>>)

Computes flow for all consecutive frame pairs in a video.

public List<Tensor<T>> EstimateFlowForVideo(List<Tensor<T>> frames)

Parameters

frames List<Tensor<T>>

Returns

List<Tensor<T>>

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

input Tensor<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).

SerializeNetworkSpecificData(BinaryWriter)

Serializes network-specific data that is not covered by the general serialization process.

protected override void SerializeNetworkSpecificData(BinaryWriter writer)

Parameters

writer BinaryWriter

The 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

input Tensor<T>

The input data.

expectedOutput Tensor<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:

  1. Makes a prediction based on the input
  2. Compares its prediction to the expected output
  3. Calculates how wrong it was (the loss)
  4. 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

parameters Vector<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.

WarpWithFlow(Tensor<T>, Tensor<T>)

Warps an image using the estimated flow.

public Tensor<T> WarpWithFlow(Tensor<T> image, Tensor<T> flow)

Parameters

image Tensor<T>
flow Tensor<T>

Returns

Tensor<T>
Edit this page