Hello @AM-adben You are right, STEdgeAI-NPU package is required in order to use Neural-ART Runtime. If the request was done more than 2 days ago, could you please check in your mailbox if this mail did not go in spam folder ? Best regards,Yanis
Thanks for your update.You are right, int8 model should consume less flash and ram.Are you using STM32CubeIDE ?If yes, you can find detailed flash consumption in Build Analyzer => Memory Details sectionsExample: On your side, could you compare "FLASH...
Hello @EnzoC,Could you please perform, on STM32CubeMX, the "Analyze" action ? You should retrieve, at the end of the textual output, the information regarding library and code size.For example: Requested memory size by section - "stm32h7" target
--...
Hello @AM-adben ,Could you please verify again your version of X-CUBE-AI ?Neural-ART Runtime should only be available from X-CUBE-AI version 10.0.0.Did you install the runtime through STM32CubeMX or STEdgeAI-Core installer ? My first suggestion would...
Hello @Lemanoise,The error previously raised in this topic is fixed with the latest version of X-CUBE-AI 10.0.0 and the release available in ST Edge AI Developer Cloud. Best regards,Yanis
