Vector implementation for Hx4 QLinearConv, requires data to be arranged in [a,b,c,d,e] -> [0,0,0,0,a,a,b,b,c,c,d,d,e,e,0,0], requires bias to be shifted, i.e. tbias - tw.reshape(M,-1).sum(1) * X_zero_point, requires INP_W%16=0, OUT_W_PAD%16=0, QLinearConv5x5Scale32bit<30,32,28,32,1,1,1,1,6,5> total = 7652.

#include <qlinearconv.h>

Public Member Functions
	QLinearConv5x5Scale32bit (TTPARAM(&w)[M C KH *16], 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, output_window< TT > out)

Static Public Member Functions
static void	registerKernelClass ()

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

design/aie_src/qlinearconv.h
design/aie_src/qlinearconv.cc

Public Member Functions

Static Public Member Functions