Int8Quantizer<T, TInput, TOutput>
Models & Types · AiDotNet.Deployment.Optimization.Quantization
INT8 quantizer for model optimization. Properly integrates with IFullModel architecture.
Implements: IQuantizer<T, TInput, TOutput>
For Beginners
Int8Quantizer provides AI safety functionality. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
Int8Quantizer() |
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) |