No implemantation of convolve_s8_kernel3_stride1_pad1_fpreq()

[wslong36]

Hey, @meenchen

I found that there is no kernel of convolve_s8_kernel3_stride1_pad1_fpreq(),

Would you mind upload this kernel of tiny engine?

Or, How should I use int_forward_op/convolve_s8_kernel3_stride1_pad1.c to implement convolve_s8_kernel3_stride1_pad1_fpreq()?

[meenchen]

Hi. @wslong36,

The only difference between fpreq and other ops is how outputs are re-quantized. fpreq means re-quantizing outputs with a fp32 scale (e.g.,

tinyengine/TinyEngine/src/kernels/fp_requantize_op/mat_mul_kernels_fpreq.c

Line 294 in fdc0019

ch_0_out_0 = (q31_t) ((float) ch_0_out_0 * scale_0);

), while other ops follow the TFLite approach.

You can also use the fp_requantize flag in code generator to disable it (e.g.,

tinyengine/examples/detection_fpn.py

Line 63 in fdc0019

fp_requantize=True,

).