arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1701.02291cs.LGstat.ML
收藏

QuickNet:最大限度地提高深层架构的效率和效能

QuickNet: Maximizing Efficiency and Efficacy in Deep Architectures

Ingemini LLC(英格米尼有限责任公司)

Tapabrata Ghosh

摘要:

我们提出了QuickNet,这是一种快速准确的网络架构,比其他快速深度架构(如SqueezeNet)更快,更准确。此外,它比以前的网络使用更少的参数,使其更具内存效率。我们通过对参考Darknet模型(Redmon et al,2015)进行两个主要修改来做到这一点:1)使用依赖可分离卷积和2)使用参数校正线性单元。我们观察到,参数整流线性单元在测试时在计算上等效于泄漏整流线性单元,并且观察到可分离卷积可以被解释为压缩的Inception网络(Chollet,2016)。利用这些观察结果,我们得出了一个网络架构,我们称之为QuickNet,它比以前的模型更快,更准确。我们的架构提供了至少四个主要的优点:(1)一个较小的模型大小,这是更适合于内存受限的系统;(2)一个显着更快的网络,这是更适合于计算受限的系统;(3)CIFAR-10数据集的准确率高达95.7%,超过了迄今为止发表的所有结果,尽管我们注意到我们的工作是正交方法,并且可以与先前的模型压缩方法相结合,从而允许实现进一步的速度增益。

英文摘要:

We present QuickNet, a fast and accurate network architecture that is both faster and significantly more accurate than other fast deep architectures like SqueezeNet. Furthermore, it uses less parameters than previous networks, making it more memory efficient. We do this by making two major modifications to the reference Darknet model (Redmon et al, 2015): 1) The use of depthwise separable convolutions and 2) The use of parametric rectified linear units. We make the observation that parametric rectified linear units are computationally equivalent to leaky rectified linear units at test time and the observation that separable convolutions can be interpreted as a compressed Inception network (Chollet, 2016). Using these observations, we derive a network architecture, which we call QuickNet, that is both faster and more accurate than previous models. Our architecture provides at least four major advantages: (1) A smaller model size, which is more tenable on memory constrained systems; (2) A significantly faster network which is more tenable on computationally constrained systems; (3) A high accuracy of 95.7 percent on the CIFAR-10 Dataset which outperforms all but one result published so far, although we note that our works are orthogonal approaches and can be combined (4) Orthogonality to previous model compression approaches allowing for further speed gains to be realized.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑