DownBlock<T>

Models & Types · AiDotNet.Diffusion.VAE

Downsampling block for VAE encoder with multiple ResBlocks and strided convolution.

Inheritance: LayerBase<T> → DownBlock<T>

Implements: IShapeContract

For Beginners

A DownBlock is like a compression stage in an encoder.

What it does:

  1. Processes the input through multiple residual blocks (learning features)
  2. Reduces spatial size by half using strided convolution (compression)

Example: 64x64 input -> 32x32 output (spatial dimensions halved)

Why use strided convolution instead of pooling?

  • Strided conv is learnable (the network decides how to downsample)
  • Max/Avg pooling has fixed behavior that may discard useful information
  • Strided conv is the standard in modern generative models like VAEs and diffusion

Structure:

input [B, C_in, H, W]
│
├─→ ResBlock → ResBlock → ... (numLayers blocks)
│
↓
[B, C_out, H, W]
│
├─→ Conv3x3 (stride=2) ─→ downsample
│
↓
output [B, C_out, H/2, W/2]

How It Works

This implements a downsampling block following the Stable Diffusion VAE architecture:

  • Multiple VAEResBlocks to process features at the current resolution
  • Strided convolution (stride=2) to reduce spatial dimensions by half

Constructors

Constructor Summary
DownBlock(int inChannels, int outChannels, int numLayers, int numGroups, int inputSpatialSize, bool hasDownsample) Initializes a new instance of the DownBlock class.

Properties

Property Summary
bool HasDownsample { get; } Gets whether this block performs downsampling.
bool SupportsTraining { get; }
int InputChannels { get; } Gets the number of input channels.
int NumLayers { get; } Gets the number of residual blocks.
int OutputChannels { get; } Gets the number of output channels.

Methods

Method Summary
IReadOnlyList<ILayer<T>> GetSubLayers()
IReadOnlyList<OutputAxisContract> OutputAxesFor(int inputRank)
IReadOnlyList<VAEResBlock<T>> GetResBlocks() Gets the residual blocks for external access (e.g., for skip connections in UNet).
void ResetState() Resets the internal state of the block.
void UpdateParameters(T learningRate) Updates all learnable parameters using gradient descent.