Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of prediction accuracy between the quantized model and the full-precision model. To address this gap, we propose to jointly train a quantized, bit-operation-compatible DNN and its associated quantizers, as opposed to using fixed, handcrafted quantization schemes such as uniform or logarithmic quantization. Our method for learning the quantizers applies to both network weights and activations with arbitrary-bit precision, and our quantizers are easy to train. The comprehensive experiments on CIFAR-10 and ImageNet datasets show that our method works consistently well for various network structures such as AlexNet, VGG-Net, GoogLeNet, ResNet, and DenseNet, surpassing previous quantization methods in terms of accuracy by an appreciable margin. Code available at https://github.com/Microsoft/LQ-Nets

本文提出了一种用于深度神经网络（DNN）压缩的联合训练方法，以便同时训练量化器和DNN，以便量化网络权重和激活，并提高量化模型的预测准确性。在CIFAR-10和ImageNet数据集上进行的全面实验显示，该方法在各种网络结构上都运行良好，超越了以前的量化方法。

LQ-Nets: 针对高准确性和紧凑型深度神经网络的学习量化