Re:XNOR.ai frees AI from the prison of the supercomputer
by emcq on Sunday January 22, 2017 @11:53PM
(#13459860)
XNOR-Net is not currently part of TensorFlow, although there is a feature request to support it. [0]
The main difference is that XNOR-Net uses 1 bit quantized weights and XNOR+popcount to approximate the dot product of convolution, which can be implemented very efficiently by using 64-bit arithmetic instructions on a CPU to operate over 64 1-bit components in parallel. [1]
TensorFlow's optimization is also using discretized weights, but AFAIK targeted at 8-bit quantized weights. [2]
The main difference is that XNOR-Net uses 1 bit quantized weights and XNOR+popcount to approximate the dot product of convolution, which can be implemented very efficiently by using 64-bit arithmetic instructions on a CPU to operate over 64 1-bit components in parallel. [1]
TensorFlow's optimization is also using discretized weights, but AFAIK targeted at 8-bit quantized weights. [2]
[0] https://github.com/tensorflow/tensorflow/issues/1592
[1] https://arxiv.org/pdf/1603.05279v4.pdf
[2] https://petewarden.com/2015/05/23/why-are-eight-bits-enough-...