【论文阅读】韩松《Efficient Methods And Hardware For Deep Learning》节选《Deep compression》

Trained Quantization and Deep Compression 本章内容来在ICLR 2016论文《Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding》。 DeepCompression由剪枝、量化和变长编码组成,它可将神经
相关文章
相关标签/搜索