onnx2versal
Loading...
Searching...
No Matches
QLinearConv1x1StreamInputPackets< TT, TTPARAM, INP_H, INP_W, OUT_W, OUT_W_PAD, STEP_H, STEP_W, B, C, M, KH, KW, GROUP > Class Template Reference

Vector implementation for 1x1 QLinearConv, streams weights requires data to be reshaped from (M,C,1,1) to (M,C') where C' is padded to next multiple of 16, requires bias to be shifted, i.e. tbias - tw_1x1.reshape(M,-1).sum(1) * X_zero_point, requires KH==KW==1, INP_W%16=0, OUT_W_PAD%16=0, STEP_H==1|2, STEP_W==1|2,.

#include <qlinearconv.h>

Public Member Functions

 QLinearConv1x1StreamInputPackets (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_pktstream *in_s, 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: