SubpixelConvolutionalLayer<T>

Layers · AiDotNet.NeuralNetworks.Layers

Represents a subpixel convolutional layer that performs convolution followed by pixel shuffling for upsampling.

Inheritance: LayerBase<T> → SubpixelConvolutionalLayer<T>

Implements: IShapeContract

For Beginners

This layer helps make images larger and more detailed in neural networks.

Think of it like rearranging a small mosaic to create a larger picture:

  • First, the layer creates many detailed patterns from the input (convolution step)
  • Then, it rearranges these patterns to form a larger, higher-resolution output (pixel shuffling step)

For example, if you’re working with a low-resolution image that’s 32×32 pixels, this layer can help transform it into a higher-resolution image of 64×64 or 128×128 pixels by intelligently filling in the details between the original pixels.

This is often used in applications like:

  • Making blurry images clearer (super-resolution)
  • Generating detailed images from rough sketches
  • Converting low-quality videos to higher quality

How It Works

A subpixel convolutional layer combines convolution with a pixel shuffling operation to efficiently increase spatial resolution of feature maps. It first applies convolution to produce an output with more channels, then rearranges these channels into a higher resolution output with fewer channels. This approach is particularly useful for super-resolution tasks and generative models where upsampling is required.

Constructors

Constructor Summary
SubpixelConvolutionalLayer(int outputDepth, int upscaleFactor, int kernelSize, IActivationFunction<T> activation) Initializes a new instance of the SubpixelConvolutionalLayer class with vector activation function.
SubpixelConvolutionalLayer(int outputDepth, int upscaleFactor, int kernelSize, IVectorActivationFunction<T> vectorActivation) Initializes a new instance of the SubpixelConvolutionalLayer class with vector activation function.

Properties

Property Summary
bool SupportsTraining { get; }

Methods

Method Summary
Dictionary<string, string> GetParameterRoles() Returns parameter roles for per-role optimizer configuration (e.g., weight decay exemption for biases).
IReadOnlyList<OutputAxisContract> OutputAxesFor(int inputRank)
IReadOnlyList<Tensor<T>> GetTrainableParameters() Returns all trainable parameter tensors marked with [TrainableParameter].
IReadOnlyList<ValueTuple<string, Tensor<T>>> GetRegisteredBuffers()
void ClearGradients()
void ResetState() Resets the internal state of the layer and reinitializes weights.
void SetTrainableParameters(IReadOnlyList<Tensor<T>> parameters) Replaces trainable parameter tensors (e.g., with ParameterBuffer views).
void UpdateParameters(T learningRate) Updates the parameters of the layer using calculated gradients and momentum.
void UpdateParametersGpu(IGpuOptimizerConfig config) Updates parameters using GPU-based optimizer.
void ZeroGrad() Clears all gradient fields discovered by convention ({paramName}Gradient).