【論文閱讀筆記】Deep Neural Network Compression with Single and Multiple Level Quantization

全文概括   本文是《Quantized Convolution Neural Networks for Mobile Devices》和《Incremental Network Quantization：Towards Lossless CNN with Low-Precision Weights》的思想結合。參考了前者的分層量化和k-means聚類共享權值，參考了後者的INQ思想，即同一層分塊

>>阅读原文<<