Class FastDVDNet<T>
FastDVDNet: Towards Real-Time Deep Video Denoising Without Flow Estimation.
public class FastDVDNet<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>, IDisposableType Parameters
TThe numeric type used for calculations.
- Inheritance
-
FastDVDNet<T>
- Implements
- Inherited Members
- Extension Methods
Remarks
For Beginners: FastDVDNet removes noise from video while preserving details and maintaining temporal consistency across frames. Unlike image denoisers, it uses multiple frames to reduce noise more effectively.
Key advantages:
- Real-time video denoising
- No optical flow computation needed
- Handles various noise levels
- Preserves temporal consistency
Example usage:
var model = new FastDVDNet<double>(arch);
var denoisedFrames = model.Denoise(noisyFrames, noiseLevel: 25);Technical Details: - Two-stage denoising pipeline - Stage 1: Denoise groups of 3 frames - Stage 2: Fuse stage 1 outputs temporally - Noise map as additional input for noise-level adaptation
Reference: "FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation" https://arxiv.org/abs/1907.01361
Constructors
FastDVDNet(NeuralNetworkArchitecture<T>, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>?, ILossFunction<T>?, int, int)
public FastDVDNet(NeuralNetworkArchitecture<T> architecture, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null, int numFeatures = 32, int numInputFrames = 5)Parameters
architectureNeuralNetworkArchitecture<T>optimizerIGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>lossFunctionILossFunction<T>numFeaturesintnumInputFramesint
FastDVDNet(NeuralNetworkArchitecture<T>, string)
public FastDVDNet(NeuralNetworkArchitecture<T> architecture, string onnxModelPath)Parameters
architectureNeuralNetworkArchitecture<T>onnxModelPathstring
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
AddGaussianNoise(Tensor<T>, double)
Adds synthetic noise to frames for testing.
public Tensor<T> AddGaussianNoise(Tensor<T> frame, double sigma)Parameters
frameTensor<T>sigmadouble
Returns
- Tensor<T>
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.
Denoise(List<Tensor<T>>, double)
Denoises a sequence of video frames.
public List<Tensor<T>> Denoise(List<Tensor<T>> frames, double noiseLevel = 25)Parameters
framesList<Tensor<T>>Noisy video frames.
noiseLeveldoubleEstimated noise standard deviation (sigma, typically 0-75).
Returns
- List<Tensor<T>>
DenoiseFrame(List<Tensor<T>>, double)
Denoises a single frame using neighboring frames.
public Tensor<T> DenoiseFrame(List<Tensor<T>> neighborFrames, double noiseLevel = 25)Parameters
Returns
- Tensor<T>
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.
EstimateNoiseLevel(Tensor<T>)
Estimates the noise level in a frame.
public double EstimateNoiseLevel(Tensor<T> frame)Parameters
frameTensor<T>
Returns
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).
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.