Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks

19 Mar 2019Sambhav R. JainAlbert GuralMichael WuChris H. Dick

We propose a method of training quantization thresholds (TQT) for uniform symmetric quantizers using standard backpropagation and gradient descent. Contrary to prior work, we show that a careful analysis of the straight-through estimator for threshold gradients allows for a natural range-precision trade-off leading to better optima... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.