本課程重要性分兩方面說明，分別是工業檢測及智慧報工。眾所皆知工業檢測在工業產品之品質管控非常重要，而工業檢測涵蓋面很廣，包括了產品外型檢驗及加工動作分析，這些應用除了要求速度也要求精確，這時智慧終端計算變得很重要，需要有強大的智慧推論計算加速。另外如何將AI訓練結果移植至SOC晶片並與感測周邊結合，是本課程目標之一。本次計畫使用聯盟C4模組之智慧終端裝置影像處理晶片設計與C7透過慣性感測器結合一AISOC晶片實現一套人體活動辨識模組，可以辨識基本的站、坐、跑步、走路、上下樓梯等活動資訊。場域應用為工業生產之動作辨識及生產數據之數位化及智慧化。分二階段教授課程模組內容，及其在智慧製造之應用。

The importance of this course is explained in two aspects, namely industrial inspection and smart reporting. As we all know, industrial inspection is very important in the quality control of industrial products, and industrial inspection covers a wide range of areas, including product appearance inspection and processing action analysis. These applications require not only speed but also accuracy. At this time, smart terminal computing becomes very important, requiring powerful smart inference calculation acceleration. In addition, how to transplant the AI ​​training results to the SOC chip and combine it with the sensing peripherals is one of the goals of this course. This project uses the alliance's C4 module's smart terminal device image processing chip design and C7 to combine an AISOC chip with an inertial sensor to implement a set of human activity recognition modules that can identify basic activity information such as standing, sitting, running, walking, and going up and down stairs. Field applications include motion recognition in industrial production and digitization and intelligence of production data. The course module content and its application in smart manufacturing will be taught in two stages.

https://github.com/FootprintAI/kubeflow-workshop

HTTPS://GitHub.com/footprint AI/crybe flow-workshop