Open mynameischaos opened 6 years ago
@mynameischaos yes, network quantization can accelerate inference speed, but your hardware must support low-precision bit shift, you can pay close attention to intel-altera and intel-movidious product.
I am curious what is the rough inference speedup on a intel cpu that support low precision bit shift, any numbers ?
how to check the cpu support "low-precision bit shift" ??@Zhouaojun
@mynameischaos yes, network quantization can accelerate inference speed, but your hardware must support low-precision bit shift, you can pay close attention to intel-altera and intel-movidious product.