ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation

Abstract

This paper proposes an efficient neural network (NN) architecture design methodology called Chameleon that honors given resource constraints. Instead of developing new building blocks or using computationally-intensive reinforcement learning algorithms, our approach leverages existing efficient network building blocks and focuses on exploiting hardware traits and adapting computation resources to fit target latency and/or energy constraints. We formulate platform-aware NN architecture search in an optimization framework and propose a novel algorithm to search for optimal architectures aided by efficient accuracy and resource (latency and/or energy) predictors. At the core of our algorithm lies an accuracy predictor built atop Gaussian Process with Bayesian optimization for iterative sampling. With a one-time building cost for the predictors, our algorithm produces state-of-the-art model architectures on different platforms under given constraints in just minutes. Our results show that adapting computation resources to building blocks is critical to model performance. Without the addition of any bells and whistles, our models achieve significant accuracy improvements against state-of-the-art hand-crafted and automatically designed architectures. We achieve 73.8% and 75.3% top-1 accuracy on ImageNet at 20ms latency on a mobile CPU and DSP. At reduced latency, our models achieve up to 8.5% (4.8%) and 6.6% (9.3%) absolute top-1 accuracy improvements compared to MobileNetV2 and MnasNet, respectively, on a mobile CPU (DSP), and 2.7% (4.6%) and 5.6% (2.6%) accuracy gains over ResNet-101 and ResNet-152, respectively, on an Nvidia GPU (Intel CPU).

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Binarized Neural Networks
• Trained Ternary Quantization
• Learning Structured Sparsity in Deep Neural Networks
• ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
• Progressive Neural Architecture Search
• CondenseNet: An Efficient DenseNet using Learned Group Convolutions
• NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks
• NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
• Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
• Grow and Prune Compact, Fast, and Accurate LSTMs

Cited by in corpus (7)

• Single Path One-Shot Neural Architecture Search with Uniform Sampling
• Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices
• VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computing
• Densely Connected Search Space for More Flexible Neural Architecture Search
• Single-Path NAS: Device-Aware Efficient ConvNet Design
• Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM
• Tuning Algorithms and Generators for Efficient Edge Inference