Other Parts Discussed in Thread: AM5728, TDA2
SDK: 06_03_00_106
Hello, TI!
I read Victor Cheng's answer in this thread https://e2e.ti.com/support/processors-group/processors/f/processors-forum/892591/tda4vm-tidl-how-can-i-get-out-q-values-scale-factors-of-layers-after-model-import/3300978?tisearch=e2e-sitesearch&keymatch=dataq#3300978. The answer said the floating output is (integer output) / (dataQ factor) / (2^quantized bit, like Q8 format, 256).
Just want to make sure if this formula is also applicable to the TIDL library in the processor sdk for AM5728?
Thanks!
