LayerQuantizationParams

Models & Types · AiDotNet.Deployment.Optimization.Quantization

Per-layer quantization parameters.

For Beginners

LayerQuantizationParams provides AI safety functionality. Default values follow the original paper settings.

Constructors

Constructor Summary
LayerQuantizationParams()

Properties

Property Summary
QuantizationMode? Mode { get; set; } Gets or sets custom quantization mode for this layer.
bool Skip { get; set; } Gets or sets whether to skip quantization for this layer.
double ScaleFactor { get; set; } Gets or sets the scale factor for this layer.
int ZeroPoint { get; set; } Gets or sets the zero point for this layer.
int? BitWidth { get; set; } Gets or sets the bit width for this layer (if different from global).