leooo

> The max-min is essentially finding the maximum absolute value. > In the code, I allow a small saturating in max-min is sometimes the value can be 1.000001 which >...

> Details of the quantisation used here can be found in ARM's blog/post about cmsis-nn and post from TFLite micro. > The difference between this one and the equation you...

Got it. Thank you very much.

mfcc setting in python: ` # get the mfcc of noisy voice mfcc_feat = mfcc(sig, sample_rate, winlen=0.032, winstep=0.032 / 2, numcep=20, nfilt=20, nfft=512, lowfreq=20, highfreq=8000, winfunc=np.hanning, ceplifter=0, preemph=0, appendEnergy=True)` mfcc...

@majianjia Thank you for your reply. I did the test following your advice and it really works. However, I found another two problems. First, with the sample input(0-512, 512 samples),...

As a footnote，my nn model is made up of four full-connected layers, so there is no hidden information like RNN. And, the result distributions of two inference engines is almost...

> the 8 bit resolution might not good for regression application. Please also try to this if It is related. #104 > > I will check in detail later when...

> Round or floor don't actually change the result because it only affects the result by 0.5/128. > In the denoise example, the output of normal gains are like this,...

> The RNN currently runs with 8bit input/output data and 16bit memory (state) data, which might keep more info. > I am not sure what is the cause of the...

@majianjia After i set x_train in 'generate_model' to x_train of training as you did in main.py example, the result of nnom infer changes a lot and is still hugely different...