Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference

22 code implementations • CVPR 2018 • Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew Howard, Hartwig Adam, Dmitry Kalenichenko

The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes.

General Classification Quantization