Float16Quantizer<T, TInput, TOutput>

Models & Types · AiDotNet.Deployment.Optimization.Quantization

FP16 (half-precision) quantizer for model optimization. Properly integrates with IFullModel architecture.

Implements: IQuantizer<T, TInput, TOutput>

For Beginners

Float16Quantizer provides AI safety functionality. Default values follow the original paper settings.

Constructors

Constructor Summary
Float16Quantizer()

Properties

Property Summary
QuantizationMode Mode { get; }
int BitWidth { get; }

Methods

Method Summary
IFullModel<T, TInput, TOutput> Quantize(IFullModel<T, TInput, TOutput> model, QuantizationConfiguration config)
double GetScaleFactor(string layerName)
int GetZeroPoint(string layerName)
void Calibrate(IFullModel<T, TInput, TOutput> model, IEnumerable<TInput> calibrationData)