This chapter introduces software platforms to be used throughout the book. We will cover this topic from two perspectives. First, we will consider PythonPython running on PC. Python will allow the reader to implement and test the desired machine learning algorithm offline. Besides, it will help the reader to visualize data obtained from sensors. Hence, it can be analyzed easily. Our second perspective will be from the microcontroller side. The microcontroller itself is of no use without being programmed. Therefore, we need an integrated development environment (IDE) working on PC. The IDE allows forming a project including all necessary support files and code for the microcontroller. We can build the project on PC and debug it on the microcontroller, if the IDE has such an option. Then, we can embed and run the generated executable file on the microcontroller. We will consider the Arduino IDE for this purpose. As the end of chapter application, we will provide tools for analyzing the generated code. Hence, the reader can measure the memory usage and inference time of a given machine learning code. This will be of great help in the following chapters.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Software to Be Used in the Book

  • Cem Ünsalan,
  • Berkan Höke,
  • Eren Atmaca

摘要

This chapter introduces software platforms to be used throughout the book. We will cover this topic from two perspectives. First, we will consider PythonPython running on PC. Python will allow the reader to implement and test the desired machine learning algorithm offline. Besides, it will help the reader to visualize data obtained from sensors. Hence, it can be analyzed easily. Our second perspective will be from the microcontroller side. The microcontroller itself is of no use without being programmed. Therefore, we need an integrated development environment (IDE) working on PC. The IDE allows forming a project including all necessary support files and code for the microcontroller. We can build the project on PC and debug it on the microcontroller, if the IDE has such an option. Then, we can embed and run the generated executable file on the microcontroller. We will consider the Arduino IDE for this purpose. As the end of chapter application, we will provide tools for analyzing the generated code. Hence, the reader can measure the memory usage and inference time of a given machine learning code. This will be of great help in the following chapters.