御風翱翔 知識漫遊

Wandering through Knowledge

Pytorch筆記: Quantization Aware Training (QAT)

Note of Quantization Aware Training (QAT) in Pytorch

pytorch作quantize運算有兩種backend選擇，分別為fbgemm以及qnnpack，分別對應x86和ARM

Posted by imprld01 Friday, December 10, 2021

FEATURED TAGS
android arm armnn compilation compile compiler cross cross-compilsation deep-learning dft fft ide installation istft java linux nn python stft
ABOUT ME
avatar

I am Bo-Wun, a software engineer. I am interested in artificial intelligence and software engineering. 😁