dnnlowp::L2ErrorMinimization Class Reference

A quantization scheme that minimizes L2 norm of quantization error. More...

#include <l2_minimization.h>

Inheritance diagram for dnnlowp::L2ErrorMinimization:

Additional Inherited Members
Public Types inherited from dnnlowp::NormMinimization
enum	Kind { L1, L2 }
Public Member Functions inherited from dnnlowp::NormMinimization
	NormMinimization (Kind kind)
TensorQuantizationParams	NonlinearQuantizationParamsSearch (const Histogram &hist, bool preserve_sparsity=false, int precision=8)
	Faster approximate search.
TensorQuantizationParams	ChooseQuantizationParams (const Histogram &hist, bool preserve_sparsity=false, int precision=8) override
Protected Attributes inherited from dnnlowp::NormMinimization
Kind	kind_

Detailed Description

A quantization scheme that minimizes L2 norm of quantization error.

Definition at line 16 of file l2_minimization.h.

---

The documentation for this class was generated from the following file:

• caffe2/quantization/server/l2_minimization.h