AFCI offline kit - Part 18: X-CUBE-AI & ST Edge AI Core
Offline development kit for an arc-fault detection / electrical-fire prevention system (current sensor -> STM32F407 ADC+DMA -> FFT/STFT features -> quantized DNN -> trip). Target offline PC: Windows 10/11 x64, CPU-only Python training.
Contents: STM32 AI tools — X-CUBE-AI 10.2.0 + ST Edge AI Core 2.2.0
ST software, downloaded by the kit owner from st.com (myST) and mirrored here unchanged for offline installation. These files are subject to ST's license agreements (e.g. SLA0048 for tools, SLA0044 for firmware), which you accept when installing. Full step-by-step instructions: INSTALLATION_GUIDE.md (in Part 6, and a copy in Part 16).
| Folder | File | What / how |
|---|---|---|
01_X-CUBE-AI_and_ST_Edge_AI_Core/ |
x-cube-ai-windows-v10.2.0.zip |
Contains STMicroelectronics.X-CUBE-AI.10.2.0.pack (install in CubeMX: Manage embedded software packages → From Local) and stedgeai-windows-10.2.0.zip = the complete offline ST Edge AI Core 2.2.0 (STM32Cube.AI 10.2.0 component): unzip to e.g. C:\ST\STEdgeAI\2.2\, add Utilities\windows to PATH, run stedgeai --version. Includes offline HTML docs in Documentation\index.html. Guide steps 4.2.4 and 7. |
02_ST_Edge_AI_Core_online_installer/ |
stedgeai-win.zip → stedgeai-windows-onlineinstaller.exe |
Online installer: needs internet at install time, so it won't work on the offline PC. Kept for later updates; use the offline package above instead. |
Typical CLI use (model → C code for the STM32F407):
stedgeai analyze -m model_int8.tflite --target stm32
stedgeai validate -m model_int8.tflite --target stm32 --mode host
stedgeai generate -m model_int8.tflite --target stm32 -o out_dir
Rebuilding split files
Files over 100 MB were split into *.part001, *.part002, ... pieces. After downloading the whole repo:
- Windows:
powershell -ExecutionPolicy Bypass -File .\join_parts.ps1 - Linux/macOS:
bash join_parts.sh
Both scripts rebuild the files and check them against SHA256SUMS.txt.
Files (2 files, 894.1 MB total)
| File | Size | Split into |
|---|---|---|
01_X-CUBE-AI_and_ST_Edge_AI_Core/x-cube-ai-windows-v10.2.0.zip |
868.9 MB | 9 |
02_ST_Edge_AI_Core_online_installer/stedgeai-win.zip |
25.2 MB | - |
Each file keeps the license of its original publisher (see the notes above).
Master index
This is one of 19 repos (AFCI_part1 … AFCI_part19). Overview of all parts: AFCI_part6 / 00_START_HERE_MASTER_INDEX.md · Installation: AFCI_part6 / 00_INSTALLATION_GUIDE.md