Neural network architecture search provides a solution to the automatic design of network structures. However, it is difficult to search the whole network architecture directly. Although using stacked cells to search neural network architectures is an effective way to reduce the complexity of searching, these methods do not able find the global optimal neural network structure since the number of layers, cells and connection methods is fixed. In this paper, we propose a Two-Stage Evolution for cell-based Network Architecture Search(TS-ENAS), including one-stage searching based on stacked cells and second-stage adjusting these cells. In our algorithm, a new cell-based search space and an effective two-stage encoding method are designed to represent cells and neural network structures. In addition, a cell-based weight inheritance strategy is designed to initialize the weight of the network, which significantly reduces the running time of the algorithm. The proposed methods are extensively tested and compared on four image classification dataset, Fashion-MNIST, CIFAR10, CIFAR100 and ImageNet and compared with 22 state-of-the-art algorithms including hand-designed networks and NAS networks. The experimental results show that TS-ENAS can more effectively find the neural network architecture with comparative performance.

我们提出了一种基于叠加单元的神经网络结构搜索的两阶段进化方法（TS-ENAS），包括基于堆叠单元的一阶段搜索和对这些单元进行调整的二阶段。在算法中，我们设计了一种新的基于单元的搜索空间和一种有效的两阶段编码方法来表示单元和神经网络结构。此外，我们设计了一种基于单元的权重继承策略来初始化网络的权重，这显著减少了算法的运行时间。我们在四个图像分类数据集Fashion-MNIST、CIFAR10、CIFAR100和ImageNet上对所提出的方法进行了广泛的测试和比较，并与包括手工设计网络和NAS网络在内的22个最新算法进行了比较。实验结果表明，TS-ENAS能更有效地找到性能相当的神经网络结构。

TS-ENAS:基于细胞的网络架构搜索的两阶段演化