Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural NetworksSambhav R. Jain, Albert Gural, Michael Wu et al.
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. Our quantizers are constrained to use power-of-2 scale-factors and per-tensor scaling of weights and activations to make it amenable for hardware implementations. We present analytical support for the general robustness of our methods and empirically validate them on various CNNs for ImageNet classification. We are able to achieve near-floating-point accuracy on traditionally difficult networks such as MobileNets with less than 5 epochs of quantized (8-bit) retraining. Finally, we present Graffitist, a framework that enables automatic quantization of TensorFlow graphs for TQT (available at https://github.com/Xilinx/graffitist ).
5.2LGMay 21, 2018
Quantizing Convolutional Neural Networks for Low-Power High-Throughput Inference EnginesSean O. Settle, Manasa Bollavaram, Paolo D'Alberto et al.
Deep learning as a means to inferencing has proliferated thanks to its versatility and ability to approach or exceed human-level accuracy. These computational models have seemingly insatiable appetites for computational resources not only while training, but also when deployed at scales ranging from data centers all the way down to embedded devices. As such, increasing consideration is being made to maximize the computational efficiency given limited hardware and energy resources and, as a result, inferencing with reduced precision has emerged as a viable alternative to the IEEE 754 Standard for Floating-Point Arithmetic. We propose a quantization scheme that allows inferencing to be carried out using arithmetic that is fundamentally more efficient when compared to even half-precision floating-point. Our quantization procedure is significant in that we determine our quantization scheme parameters by calibrating against its reference floating-point model using a single inference batch rather than (re)training and achieve end-to-end post quantization accuracies comparable to the reference model.