🚀 Just completed a full pipeline for YOLOv5 on the #RK3568!

From local training on Windows to real-time NPU inference on the dev board.

✅ YOLOv5 Custom Training
✅ .pt ➡️ .onnx ➡️ .rknn conversion
✅ RKNN-Toolkit2 & RKNPU2 optimization
✅ Successful board-level deployment

The RK3568 is a beast for edge AI when the conversion is done right! 🛠️💻
https://www.forlinx.net/industrial-news/yolov5-training-rk3568-rknn-deployment-guide-775.html

#AIoT #EmbeddedSystems #YOLOv5 #Rockchip #ComputerVision #EdgeAI

🔌 Simplified & cost-effective device-to-device communication on the #Rockchip OK3588 platform using USB NIC virtualization! 🚀

✅ Fast TCP/IP comms
✅ Cross-platform collaboration (OK3588 + RK3562)
✅ Easy debugging & remote maintenance
https://www.forlinx.net/industrial-news/ok3588-rk3562-usb-nic-communication-770.html

Accelerate embedded systems development! 🔧 #EmbeddedSystems #TechInnovation #Networking #USB #Rockchip #IoT

On i.MX8MP, GPIOs are owned by Linux (A53) by default.
If the Cortex-M7 needs them—especially for interrupts—you must release them in the device tree:

• Remove pinmux
• Remove GPIO references
• Disable the GPIO controller if needed

This prevents A53/M7 resource conflicts and ensures real-time reliability.
https://www.forlinx.net/industrial-news/imx8mp-m7-gpio-release-linux-pinmux-769.html

#iMX8MP #CortexM7 #EmbeddedLinux #GPIO #RTOS

🚀 Running Nginx on OKMX6ULx Embedded Linux (Kernel 4.1.15)!

✅ Yocto compilation
✅ Reverse proxy to Tomcat 9
✅ Load balancing across 8080 & 8081

Embedded boards can handle high-performance web services too!
https://www.forlinx.net/industrial-news/nginx-okmx6ulx-porting-768.html

#EmbeddedLinux #Nginx #IoT #LoadBalancing #ReverseProxy #OKMX6ULx

Flashing Linux images on RK3568 made simple ⚙️
This guide shows how to flash boot.img & rootfs.img via TFTP + U-Boot on the Forlinx RK3568 dev board.

✔️ Fast network flashing
✔️ Clear eMMC partitioning
✔️ Industrial-grade reliability
✔️ Ready for AI & edge apps
https://www.forlinx.net/industrial-news/forlinx-rk3568-tftp-flash-guide-766.html

#RK3568 #EmbeddedLinux #Forlinx #TFTP #UBoot #IoT #EdgeAI

Traffic demand changes in seconds — lane control should too 🚦

The FCU3501 AI edge computing box brings real-time, autonomous decision-making to intelligent flexible lanes using edge AI, not cloud latency.
https://www.forlinx.net/industrial-news/fcu3501-ai-edge-computing-intelligent-flexible-lanes-762.html

#EdgeAI #SmartTraffic #SmartCity #EdgeComputing

Rockchip’s new RV1126B sets a new benchmark for Edge AI vision.
Faster CPU, 3TOPS NPU, AI-ISP, ultra-low-light imaging, 8MP@45fps, AOV 3.0, and built-in security.

Perfect for smart security, industrial vision, robotics & in-vehicle systems.

Forlinx solutions coming soon. Stay tuned! 🚀
https://www.forlinx.net/industrial-news/rockchip-rv1126b-ai-vision-processor-upgrade-754.html

#EdgeAI #AIoT #RV1126B #Rockchip #SmartSecurity #Robotics #VisionAI

Introducing the Forlinx FCU3501 — an industrial-grade edge control unit powered by RK3588J.

✔️ Wide-temp: -40°C to +85°C
✔️ Fanless, robust thermal design
✔️ Passed ESD/EFT/Surge tests
✔️ 10,000+ cold restarts, 0 failures
✔️ CE & FCC certified

High performance + industrial reliability = FCU3501
Perfect for edge AI, automation, and harsh environments.
#IndustrialAutomation #EdgeComputing #EmbeddedSystems #IndustrialPC #RK3588
#EmbeddedAI #IndustrialAI

https://www.forlinx.net/industrial-news/fcu3501-industrial-edge-controller-rk3588j-753.html