开发板是imx8M mini，我们自己做的板子，使用官方镜像yocto 4.14.98，OV5640 mipi摄像头，验证及其测试：

root@imx8mmevk:~# uname -a
Linux imx8mmevk 4.14.98-imx_4.14.98_2.0.0_ga+g5d6cbea #1 SMP PREEMPT Thu Dec 12 08:23:58 UTC 2019 aarch64 aarch64 aarch64 GNU/Linux

我这里用的是I2C4的接口，所以设备树修改arch/arm64/boot/dts/freescale/fsl-imx8mm-evk.dts

Have you ever checked your smartphone or your IoT device and received an alert for software updates? All you have to do is to simply accept the update when you have the network connectivity and the rest will be taken care of automatically by the software. Isn’t it simply amazing to be able to refresh your device, no matter where you are in the world? This update process is widely known as OTA (over the air).

OTA is a technology that manages software and lets you wirelessly upgrade the operating system/files of your platform.

iWave systems recently launched a new SMARC System on Module (SOM) based on the powerful NXP® i.MX 8QuadMax applications processors. This high performance SOM features an intelligent blend of MPUs+MCU power in a single device and integrates heterogeneous multicore 64 bit ARM® processors (Dual Cortex® A72@ 1.8 GHz + Quad Cortex® A53 @ 1.2 GHz and Dual Cortex® -M4F @ 266 MHz), targeted for applications that demand advanced real-time processing, multi-media performance as well as in applications that requires simultaneous multi-OS operations. For more details refer to the link: i.MX8 QuadMax NXP SMARC SOM

iWave Systems, a leading embedded solutions provider company based in Bangalore has successfully demonstrated Xen virtualization hypervisor on their i.MX8 QM SoC based System on Module. The  multi-core SOM comprises of 2x Arm^® Cortex^® -A72 @1.8 GHz and 4x Arm^® Cortex^®-A53 @1.2 GHz and 2x additional Cortex^®-M4F @ 266 MHz, rendering a highly powerful  integrated solution on a SMARC R2.0 compatible module.

This tutorial demonstrates how to convert a Tensorflow model to TensorFlow Lite using post training quantization and run the inference on an i.MX8 board using the eIQ™ ML Software Development Environment. It uses a TensorFlow mobilenet_v1 model pre-trained with ImageNet.

NOTES:

1. Except for the section "Build Custom Application to Run the Inference" this tutorial can also be applied to any i.MX RT platform.

2. For more information on quantization check the 'QuantizationOverview.pdf' attached to this post.

Machine Learning at the Edge:

eIQ Software for i.MX Applications Processors

Developing machine learning (ML) applications for embedded devices can be a daunting task. For the traditional embedded developer, the learning curve can be quite steep, as there are numerous decisions that must be made and new jargon that must be learned. Which framework should I choose? Which model best meets the requirements of my application and how do I know when it’s good enough? What “size” microcontroller or application processor do I need? The questions are many and figuring out how to get started can prove to be a challenge.

GmSSL is an open source cryptographic toolbox that supports SM2 / SM3 / SM4 / SM9 and other national secret (national commercial password) algorithm, SM2 digital certificate and SM2 certificate based on SSL / TLS secure communication protocol to support the national security hardware password device , To provide in line with the national standard programming interface and command line tools, can be used to build PKI / CA, secure communication, data encryption and other standards in line with national security applications. For more information, please access GmSSL official website http://gmssl.org/english.html.

GmSSL是一个开源的密码工具箱，支持SM2/SM3/SM4/SM9/ZUC等国密(国家商用密码)算法、SM2国密数字证书及基于SM2证书的SSL/TLS安全通信协议，提供符合国密规范的编程接口与命令行工具，可以用于构建PKI/CA、安全通信、数据加密等符合国密标准的安全应用。GmSSL项目是OpenSSL项目的分支，并与OpenSSL保持接口兼容。因此GmSSL可以替代应用中的OpenSSL组件，并使应用自动具备基于国密的安全能力。GmSSL项目采用对商业应用友好的类BSD开源许可证，开源且可以用于闭源的商业应用。