Single-Path NAS: Device-Aware Efficient ConvNet Design
Single-Path NAS: Device-Aware Efficient ConvNet Design
复制标题
DOI：
--
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Dimitrios Stamoulis;Ruizhou Ding;Di Wang;Dimitrios Lymberopoulos;B. Priyantha;Jie Liu-;Diana Marculescu
中科院分区：
文献类型：
--
作者：
Dimitrios Stamoulis;Ruizhou Ding;Di Wang;Dimitrios Lymberopoulos;B. Priyantha;Jie Liu-;Diana Marculescu
我们可以在移动设备的延迟约束下自动设计具有最高图像分类精度的卷积网络（Convnet）吗？ Convnet设计的神经体系结构搜索（NAS）是一个具有挑战性的问题，因为组合较大的设计空间和搜索时间（至少200个GPU小时）。为了减轻这种复杂性，我们提出了单路NAS，这是一种新型的可区分NAS方法，用于在不到4个小时内设计设备有效的交流器。 1。新颖的NAS公式：我们的方法引入了单个路径，过度参数化的convnet，以用共享的卷积内核参数编码所有架构决策。 2。NAS效率：我们的方法将NAS搜索成本降低到8个时期（30吨小时），即与先前的工作相比快5,000倍。 3。启动图像分类：与具有相似延迟的NAS方法相比，单路径NAS在Imagenet上具有79毫秒推理潜伏期的ImageNet上的TOP-1精度为74.96％（<<<<<） 80ms）。
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device? Neural Architecture Search (NAS) for ConvNet design is a challenging problem due to the combinatorially large design space and search time (at least 200 GPU-hours). To alleviate this complexity, we propose Single-Path NAS, a novel differentiable NAS method for designing device-efficient ConvNets in less than 4 hours. 1. Novel NAS formulation: our method introduces a single-path, over-parameterized ConvNet to encode all architectural decisions with shared convolutional kernel parameters. 2. NAS efficiency: Our method decreases the NAS search cost down to 8 epochs (30 TPU-hours), i.e., up to 5,000x faster compared to prior work. 3. On-device image classification: Single-Path NAS achieves 74.96% top-1 accuracy on ImageNet with 79ms inference latency on a Pixel 1 phone, which is state-of-the-art accuracy compared to NAS methods with similar latency (<80ms).