onnx2versal
Loading...
Searching...
No Matches
QLinearConvScalarStream< TT, TTPARAM, INP_H, INP_W, OUT_W, OUT_W_PAD, STEP_H, STEP_W, B, C, M, KH, KW, GROUP > Class Template Reference

Scalar implementation streaming weights, requires weights stream to be padded from MxCxKxK to MxCx16, KH=KW < 5, requires bias to be shifted, i.e. tbias - tw.reshape(M,-1).sum(1) * X_zero_point, QLinearConvScalarStream<28,32,28,32,1,1,1,1,6,3> total = 776955 (output_window 682564)

#include <qlinearconv.h>

Public Member Functions

 QLinearConvScalarStream (int32_t(&b)[M], float x_scale, float w_scale, float y_scale, TT x_zero, TTPARAM w_zero, TT y_zero)
 
void filter (input_window< TT > *in, input_stream< TTPARAM > *weights, output_stream< TT > *out)
 

Static Public Member Functions

static void registerKernelClass ()
 

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