pytorch  1.8.2
About: PyTorch provides Tensor computation (like NumPy) with strong GPU acceleration and Deep Neural Networks (in Python) built on a tape-based autograd system. LTS (Long Term Support) release.
  Fossies Dox: pytorch-1.8.2.tar.gz  ("unofficial" and yet experimental doxygen-generated source code documentation)  

pytorch_qnnp_conv_quantization_params Union Reference

#include <params.h>

Collaboration diagram for pytorch_qnnp_conv_quantization_params:
[legend]

Public Attributes

struct {
   const uint8_t *   kernel_zero_points
 
   int32_t   input_zero_point
 
   const float *   requantization_scales
 
   int32_t   output_min_less_zero_point
 
   int32_t   output_max_less_zero_point
 
   int32_t   output_zero_point
 
scalar
 

Detailed Description

Definition at line 129 of file params.h.

Member Data Documentation

◆ input_zero_point

int32_t pytorch_qnnp_conv_quantization_params::input_zero_point

◆ kernel_zero_points

const uint8_t* pytorch_qnnp_conv_quantization_params::kernel_zero_points

◆ output_max_less_zero_point

int32_t pytorch_qnnp_conv_quantization_params::output_max_less_zero_point

Definition at line 135 of file params.h.

◆ output_min_less_zero_point

int32_t pytorch_qnnp_conv_quantization_params::output_min_less_zero_point

Definition at line 134 of file params.h.

◆ output_zero_point

int32_t pytorch_qnnp_conv_quantization_params::output_zero_point

◆ requantization_scales

const float* pytorch_qnnp_conv_quantization_params::requantization_scales

◆ 

struct { ... } pytorch_qnnp_conv_quantization_params::scalar

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