SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size
复制标题
DOI：
--
复制
发表时间：
2016-02
期刊：
影响因子：
--
通讯作者：
F. Iandola;Matthew W. Moskewicz;Khalid Ashraf;Song Han;W. Dally;K. Keutzer
中科院分区：
文献类型：
--
作者：
F. Iandola;Matthew W. Moskewicz;Khalid Ashraf;Song Han;W. Dally;K. Keutzer
最近对深度神经网络的研究主要集中在提高准确性上。对于给定的准确度水平，通常可以识别实现该准确度水平的多个DNN架构。在同等精度的情况下，较小的DNN架构至少提供了三个优势：（1）较小的DNN在分布式训练期间需要更少的服务器通信。(2)较小的DNN需要更少的带宽将新模型从云端导出到自动驾驶汽车。(3)较小的DNN更适合部署在FPGA和其他内存有限的硬件上。为了提供所有这些优点，我们提出了一个名为SqueezeNet的小型DNN架构。SqueezeNet在ImageNet上实现了AlexNet级别的准确性，参数减少了50倍。此外，通过模型压缩技术，我们能够将SqueezeNet压缩到小于0.5MB（比AlexNet小510倍）。SqueezeNet架构可在此处下载：此https URL
Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that accuracy level. With equivalent accuracy, smaller DNN architectures offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware with limited memory. To provide all of these advantages, we propose a small DNN architecture called SqueezeNet. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB (510x smaller than AlexNet). The SqueezeNet architecture is available for download here: this https URL