Neural Architecture Search for Intel Movidius VPU
Hardware-aware Neural Architecture Search (NAS) technologies have been proposed to automate and speed up model design to meet both quality and inference efficiency requirements on a given hardware. Prior arts have shown the capability of NAS on hardware specific network design. In this whitepaper, we further extend the use of NAS to Intel Movidius VPU (Vision Processor Units). To determine the hardware-cost to be incorporated into the NAS process, we introduced two methods: pre-collected hardware-cost on device and device-specific hardware-cost model VPUNN. With the help of NAS, for classification task on VPU, we can achieve 1.3x fps acceleration over Mobilenet-v2-1.4 and 2.2x acceleration over Resnet50 with the same accuracy score. For super resolution task on VPU, we can achieve 1.08x PSNR and 6x higher fps compared with EDSR3.
Code (0)
등록된 구현이 없습니다.
Tasks
Hardware Aware Neural Architecture SearchNeural Architecture SearchSuper-ResolutionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Cluster Pruning: An Efficient Filter Pruning Method for Edge AI Vision Applications
Even though the Convolutional Neural Networks (CNN) has shown superior results in the field of computer vision, it is still a challenging task to implement computer vision algorithms in real-time at the edge, especially …
CPUGPUQuantizationDeployment-Aligned Low-Precision Neural Architecture Search for Spaceborne Edge AI
Designing deep networks that meet strict latency and accuracy constraints on edge accelerators increasingly relies on hardware-aware optimization, including neural architecture search (NAS) guided by device-level metrics…
Neural Architecture SearchBenchmarking Keyword Spotting Efficiency on Neuromorphic Hardware
Using Intel's Loihi neuromorphic research chip and ABR's Nengo Deep Learning toolkit, we analyze the inference speed, dynamic power consumption, and energy cost per inference of a two-layer neural network keyword spotter…
BenchmarkingCPUGPUKeyword SpottingTEA-DNN: the Quest for Time-Energy-Accuracy Co-optimized Deep Neural Networks
Embedded deep learning platforms have witnessed two simultaneous improvements. First, the accuracy of convolutional neural networks (CNNs) has been significantly improved through the use of automated neural-architecture …
General Classificationimage-classificationImage ClassificationNeural Architecture SearchEmbedded Deep Learning for Face Detection and Emotion Recognition with Intel© Movidius (TM) Neural Compute Stick
Nowadays deep learning is one of the main topics in almost every field. It helped to get amazing results in a great number of tasks. The main problem is that this kind of learning and consequently neural networks, that c…
Deep LearningEmotion RecognitionFace Detection