论文标题
DP-NET：动态编程指导深度神经网络压缩
DP-Net: Dynamic Programming Guided Deep Neural Network Compression
论文作者
论文摘要
在这项工作中，我们提出了一个有效的方案（称为DP-NET），用于压缩深神经网络（DNNS）。它包括一种新型的动态编程（DP）算法，以获得权重量化的最佳解决方案和训练聚类友好型DNN的优化过程。实验表明，DP-NET比最先进的同时具有更大的压缩，同时保持准确性。通过将DP-NET与其他压缩技术相结合，可以实现广泛重新NET上最大的77倍压缩率。此外，DP-NET被扩展用于压缩具有可忽略的精度损失的稳健DNN模型。最后，在FPGA上设计了一个自定义加速器，以加快使用DP-NET的推理计算。
In this work, we propose an effective scheme (called DP-Net) for compressing the deep neural networks (DNNs). It includes a novel dynamic programming (DP) based algorithm to obtain the optimal solution of weight quantization and an optimization process to train a clustering-friendly DNN. Experiments showed that the DP-Net allows larger compression than the state-of-the-art counterparts while preserving accuracy. The largest 77X compression ratio on Wide ResNet is achieved by combining DP-Net with other compression techniques. Furthermore, the DP-Net is extended for compressing a robust DNN model with negligible accuracy loss. At last, a custom accelerator is designed on FPGA to speed up the inference computation with DP-Net.
