Table of Contents

Class FLAVR<T>

Namespace
AiDotNet.Video.FrameInterpolation
Assembly
AiDotNet.dll

FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation.

public class FLAVR<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
FLAVR<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: FLAVR interpolates frames between existing video frames to create smoother slow-motion effects or increase video frame rate. Unlike other methods that explicitly estimate optical flow, FLAVR directly synthesizes intermediate frames.

Key advantages:

  • No explicit optical flow computation (faster)
  • Can generate multiple intermediate frames at once
  • Uses 3D convolutions for spatiotemporal understanding
  • Handles large motions better than flow-based methods

Example usage:

var model = new FLAVR<double>(arch);
var interpolatedFrames = model.Interpolate(frame1, frame2, numInterpolations: 3);

Technical Details: - 3D encoder-decoder architecture with skip connections - Multi-scale feature extraction - Direct frame synthesis without flow estimation

Reference: "FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation" https://arxiv.org/abs/2012.08512

Constructors

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

public FLAVR(NeuralNetworkArchitecture<T> architecture, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null, int numFeatures = 64, int numInputFrames = 4, int numOutputFrames = 1)

Parameters

architecture NeuralNetworkArchitecture<T>
optimizer IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>
lossFunction ILossFunction<T>
numFeatures int
numInputFrames int
numOutputFrames int

FLAVR(NeuralNetworkArchitecture<T>, string, int) 

public FLAVR(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, int numOutputFrames = 1)

Parameters

architecture NeuralNetworkArchitecture<T>
onnxModelPath string
numOutputFrames int

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.

DoubleFrameRate(List<Tensor<T>>)

Doubles the frame rate of a video.

public List<Tensor<T>> DoubleFrameRate(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.

Interpolate(Tensor<T>, Tensor<T>, int)

Interpolates frames between two input frames using recursive neural network synthesis.

public List<Tensor<T>> Interpolate(Tensor<T> frame1, Tensor<T> frame2, int numInterpolations = 1)

Parameters

frame1 Tensor<T>
frame2 Tensor<T>
numInterpolations int

Returns

List<Tensor<T>>

Remarks

Uses recursive binary interpolation where each intermediate frame is synthesized by the neural network, not just linearly blended. This produces higher quality results for multi-frame interpolation compared to simple blending.

Algorithm for numInterpolations=N: 1. Compute the midpoint frame using the neural network 2. Recursively interpolate the left half (frame1 to midpoint) 3. Recursively interpolate the right half (midpoint to frame2) 4. Combine results in temporal order

InterpolateAtTimestep(Tensor<T>, Tensor<T>, double, int)

Interpolates at a specific temporal position using adaptive refinement.

public Tensor<T> InterpolateAtTimestep(Tensor<T> frame1, Tensor<T> frame2, double t, int maxRecursionDepth = 4)

Parameters

frame1 Tensor<T>

First frame (at t=0).

frame2 Tensor<T>

Second frame (at t=1).

t double

Target timestep in range (0, 1).

maxRecursionDepth int

Maximum recursion depth for refinement.

Returns

Tensor<T>

Synthesized frame at temporal position t.

Remarks

Uses hierarchical interpolation to synthesize a frame at an arbitrary timestep t. For t close to 0.5, uses direct network output. For other values, recursively refines by interpolating between synthesized frames.

InterpolateWith4Frames(Tensor<T>, Tensor<T>, Tensor<T>, Tensor<T>)

Interpolates frames using 4 input frames for better quality.

public Tensor<T> InterpolateWith4Frames(Tensor<T> f0, Tensor<T> f1, Tensor<T> f2, Tensor<T> f3)

Parameters

f0 Tensor<T>
f1 Tensor<T>
f2 Tensor<T>
f3 Tensor<T>

Returns

Tensor<T>

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.

Edit this page