HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
Zhaohui Yang, Yunhe Wang, Xinghao Chen, Jianyuan Guo, Wei zhang, Chao Xu, Chunjing Xu, DaCheng Tao, Chang Xu
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/Mind23-2/MindCode-101/tree/main/HourNASmindspore★ 0
- github.com/2023-MindSpore-1/ms-code-214/tree/main/HourNASmindspore★ 0
- github.com/code-implementation1/Code4/tree/main/HourNASmindspore★ 0
- github.com/Mind23-2/MindCode-3/tree/main/HourNASmindspore★ 0
- github.com/2023-MindSpore-4/Code-5/tree/main/HourNASmindspore★ 0
- github.com/mindspore-ai/models/tree/master/research/cv/HourNASmindspore★ 0
Abstract
Neural Architecture Search (NAS) refers to automatically design the architecture. We propose an hourglass-inspired approach (HourNAS) for this problem that is motivated by the fact that the effects of the architecture often proceed from the vital few blocks. Acting like the narrow neck of an hourglass, vital blocks in the guaranteed path from the input to the output of a deep neural network restrict the information flow and influence the network accuracy. The other blocks occupy the major volume of the network and determine the overall network complexity, corresponding to the bulbs of an hourglass. To achieve an extremely fast NAS while preserving the high accuracy, we propose to identify the vital blocks and make them the priority in the architecture search. The search space of those non-vital blocks is further shrunk to only cover the candidates that are affordable under the computational resource constraints. Experimental results on the ImageNet show that only using 3 hours (0.1 days) with one GPU, our HourNAS can search an architecture that achieves a 77.0% Top-1 accuracy, which outperforms the state-of-the-art methods.