What you’ll learn
- 利用Max78000的机器学习支持有多容易？
- 什么类型的工具提供MAX78000?
我倾向于每年只做几篇动手文章，因此我寻找开发人员想要检查的尖端平台。Maxim Integrated’sMAX78000 evaluation kitfits in this bucket. The MAX78000 is essentially an Arm Cortex-M4F microcontroller with a lot of hardware around it, including a convolutional-neural-network (CNN) accelerator designed by Maxim(Fig. 1)。This machine-learning (ML) support allows the chip to handle chores like identifying voice keywords or even faces in camera images in real time without busting the power budget.
这chip also includes a RISC-V core that caught my eye. However, the development tools are so new that the RISC-V support is still in the works as the Cortex-M4F is the main processor. Even the CNN support is just out of the beta stage, but that's where this article will concentrate on.
MAX78000具有通常的微控制器外围配置，包括一系列串行端口，计时器和平行串行接口（如i）2S.它甚至具有平行的摄像头界面。在模拟外围设备中，有8通道，10位Sigma-Delta ADC。也有四个比较器。
这chip has large 512-kB flash memory along with 128 kB of SRAM and a boot ROM that allows more complex boot procedures such as secure boot support. There's on-chip key storage as well as CRC and AES hardware support. We will get into the CNN support a little later. TheGithub-based documentationcovers some of the features I outline here in step-by-step detail.
开发工具是免费的，并基于Eclipse, which is the basis for other platforms likeTexas Instruments'Code Composer Studio andSilicon Labs’简单工作室。Maxim并没有做很多自定义，但是足以促进使用Max78000之类的硬件，同时易于使用第三方插件和工具，在处理云或物联网开发环境时，这可能非常方便。默认安装包括示例和教程，可轻松测试CNN硬件和其他外围设备。
Max78000开发委员会具有两个LCD显示屏。较大的3.5英寸TFT触摸触摸显示器适用于处理器，而第二个较小的显示屏则提供了电源管理信息。该芯片没有内置的显示控制器，因此它使用串行接口与较大的显示器一起使用。电力跟踪支持是复杂的，但我现在不会深入研究。
这re's a 16-MB QSPI flash chip that can be handy for storing image data. In addition, a USB bridge to the flash chip allows for faster and easier downloads.
这board also adds some useful devices like a digital microphone, a 3D accelerometer, and 3D gyro. Several buttons and LEDs round out the peripherals.
这re are a couple JTAG headers; the RISC-V core has its own. As noted, I didn’t play with the RISC-V core this time around as it's not required for using the CNN support—although it could. Right now, the Maxim tools generate C code for the Cortex-M4F to set up the CNN hardware. The CNN hardware is designed to handle a single model, but it's possible to swap in new models quickly.
As with most ML hardware, the underlying hardware tends to be hidden from most programmers, providing more of a black-box operation where you set up the box and feed it data with results coming out the other end. This works well if the models are available; it's a matter of training them with different information or using trained models. The challenge comes when developing and training new models, which is something I'll avoid discussing here.
I did try out two of the models provided by Maxim, including aKeyword Spotting和Face Identification (FaceID)应用。关键字发现应用程序本质上是语音识别系统，可用于侦听关键字以开始基于云的讨论，这是大多数基于Alexa的语音系统的工作方式，因为云在识别关键字后处理所有内容。
On the other hand, being able to recognize a number of different keywords makes it possible to build a voice-based command system, such as those used in many car navigation systems. As usual, the Cortex-M4F handles the input and does a bit of munging to provide suitable inputs to the CNN accelerator(Fig. 2)。检测到的类输出指定识别哪些关键字，如果有的话。然后，应用程序可以利用此信息。
Faceid系统突出显示了Max78000的相机支持(Fig. 3)。这可以用来识别面部或识别在装配线上移动的特定零件。示例应用程序可以使用罐头输入（如图所示）或从相机中运行。
使用默认值与编译和编程芯片一样容易。Maxim提供所有示例代码和过程。这些可以在某种程度上进行修改，但是重新训练模型是一种更具涉及的练习，尽管Maxim的文档确实涵盖了一个模型。这些示例提供了需要完成的工作以及自定义解决方案需要更改的概述。
将模型和应用更改为像电动机振动监控系统之类的东西将是一项需要新型号的重要工作，但是芯片可能能够处理。它将需要更多的机器学习和CNN支持，因此，这不是应该轻易采取的。
该工具集支持来自TensorFlow和Pytorch等平台的模型(Fig. 4)。这是非常有用的,因为培训不处理the chip, but rather done on platforms like a PC or cloud servers. Likewise, the models can be refined and tested on higher-end hardware to verify the models, which can then be pruned to fit on the MAX78000.
At this point, the CNN accelerator documentation is a bit sparse, as is the RISC-V support. Maxim’s CNN model compiler kicks out C code that drops in nicely to the Eclipse IDE. Debugging the regular application code is on par with other cross-development systems where remote debugging via JTAG is the norm.
Maxim also provides theMAX78000FTHR, the little brother of the evaluation kit（图5），这没有显示屏或其他外围硬件，但是大多数I/O都暴露了。仅董事会只有25美元。该芯片的价格少于15美元。这Github-based documentationprovides more details.
Max78000很有趣。这是支持边缘上ML应用程序的绝佳平台。但是，请注意，虽然这是一个非常低的功率解决方案，但即使是低端也不一样Nvidia Jetson Nano。查看电动跟踪支持将很有趣，因为在许多Max78000应用程序（尤其是基于电池的解决方案）中，功率利用率和需求可能是关键因素。
