In this work, we investigate the inference time of the MobileNet family, EfficientNet V1 and V2 family, VGG models, Resnet family, and InceptionV3 on four edge platforms. Specifically NVIDIA Jetson Nano, Intel Neural Stick, Google Coral USB Dongle, and Google Coral PCIe. Our main contribution is a thorough analysis of the aforementioned models in multiple settings, especially as a function of input size, the presence of the classification head, its size, and the scale of the model. Since throughout the industry, those architectures are mainly utilized as feature extractors we put our main focus on analyzing them as such. We show that Google platforms offer the fastest average inference time, especially for newer models like MobileNet or EfficientNet family, while Intel Neural Stick is the most universal accelerator allowing to run most architectures. These results should provide guidance for engineers in the early stages of AI edge systems development. All of them are accessible at https://bulletprove.com/research/edge_inference_results.csv

翻译：本研究探讨了MobileNet系列、EfficientNet V1和V2系列、VGG模型、ResNet系列以及InceptionV3在四种边缘平台上的推理时间，具体包括NVIDIA Jetson Nano、Intel Neural Stick、Google Coral USB Dongle和Google Coral PCIe。我们的主要贡献在于对上述模型在多种设置下的全面分析，特别是作为输入尺寸、分类头存在性及其大小、以及模型规模的函数。鉴于业界主要将这些架构用作特征提取器，我们重点对其在该场景下的性能进行了分析。结果表明，Google平台提供了最快的平均推理时间，尤其是对于MobileNet或EfficientNet系列等较新模型，而Intel Neural Stick则是适应性最广的加速器，能够运行大多数架构。这些结果应为工程师在AI边缘系统开发的早期阶段提供指导。所有结果均可通过https://bulletprove.com/research/edge_inference_results.csv 获取。