Neural Architecture Search (NAS) yields state-of-the-art neural networks that outperform their best manually-designed counterparts. However, previous NAS methods search for architectures under one set of training hyper-parameters (i.e., a training recipe), overlooking superior architecture-recipe combinations. To address this, we present Neural Architecture-Recipe Search (NARS) to search both (a) architectures and (b) their corresponding training recipes, simultaneously. NARS utilizes an accuracy predictor that scores architecture and training recipes jointly, guiding both sample selection and ranking. Furthermore, to compensate for the enlarged search space, we leverage "free" architecture statistics (e.g., FLOP count) to pretrain the predictor, significantly improving its sample efficiency and prediction reliability. After training the predictor via constrained iterative optimization, we run fast evolutionary searches in just CPU minutes to generate architecture-recipe pairs for a variety of resource constraints, called FBNetV3. FBNetV3 makes up a family of state-of-the-art compact neural networks that outperform both automatically and manually-designed competitors. For example, FBNetV3 matches both EfficientNet and ResNeSt accuracy on ImageNet with up to 2.0x and 7.1x fewer FLOPs, respectively. Furthermore, FBNetV3 yields significant performance gains for downstream object detection tasks, improving mAP despite 18% fewer FLOPs and 34% fewer parameters than EfficientNet-based equivalents.
翻译:神经结构搜索(NAS) 产生最先进的神经神经网络, 其效果优于最佳手工设计的神经网络。 然而, 以前的NAS 方法在一组培训超参数( 即培训配方) 下寻找建筑, 忽略了高级建筑- 反应组合。 为此, 我们提出神经建筑- 搜索( NAS), 以同时搜索 (a) 建筑和 (b) 相应的培训配方。 NARS 使用一个精确预测, 分数结构和培训配方, 指导抽样选择和排名。 此外, 为了弥补扩大的搜索空间, 我们利用“ 免费” 结构统计( 如培训配方 ), 以预设预测器, 大幅提高其样本效率和预测可靠性。 在通过限制迭代优化培训预测器后, 我们仅用CPU 分钟进行快速进化搜索, 以生成基于更少资源制约的架构- 配对, 调用 FBNetV3 FB 。 FB 网络3 组成一个更小的州级结构-, 精度 精度 精度 精度 精度 精度 FROFROF- 3