论文标题
AI模型和框架在移动设备上的比较和基准测试
Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices
论文作者
论文摘要
由于数据量增加和计算资源，深度学习在各个领域都取得了许多成功。在移动和嵌入式设备上进行深度学习的应用越来越注意，对移动设备和嵌入式设备的AI能力进行基准测试和排名成为要解决的紧迫问题。考虑到模型多样性和框架多样性，我们提出了一个基准套件AiotBench，该套件的重点是评估移动设备和嵌入式设备的推理能力。 AiotBench涵盖了三个典型的重量重量网络：Resnet50，InceptionV3，Densenet121，以及三个轻量级网络：Squeezenet，MobilenetV2，Mnasnet。每个网络均由为移动设备和嵌入式设备设计的三个框架实现：Tensorflow Lite，Caffe2，Pytorch Mobile。为了比较和对设备的AI功能进行比较，我们提出了两个统一的指标作为AI分数：每秒有效图像（VIP）和每秒有效的Flops（VOPS）（VOPS）。目前，我们使用基准进行了比较并对5个移动设备进行了排名。此列表将在不久之后延长和更新。
Due to increasing amounts of data and compute resources, deep learning achieves many successes in various domains. The application of deep learning on the mobile and embedded devices is taken more and more attentions, benchmarking and ranking the AI abilities of mobile and embedded devices becomes an urgent problem to be solved. Considering the model diversity and framework diversity, we propose a benchmark suite, AIoTBench, which focuses on the evaluation of the inference abilities of mobile and embedded devices. AIoTBench covers three typical heavy-weight networks: ResNet50, InceptionV3, DenseNet121, as well as three light-weight networks: SqueezeNet, MobileNetV2, MnasNet. Each network is implemented by three frameworks which are designed for mobile and embedded devices: Tensorflow Lite, Caffe2, Pytorch Mobile. To compare and rank the AI capabilities of the devices, we propose two unified metrics as the AI scores: Valid Images Per Second (VIPS) and Valid FLOPs Per Second (VOPS). Currently, we have compared and ranked 5 mobile devices using our benchmark. This list will be extended and updated soon after.
