Edge AI

We have been evaluating the pre-trained model yamnet_e1024_64x96_tl_qdq_int8.onnx from the STM32 Model Zoo (ESC-10 variant) and noticed a potential discrepancy between the class label order in the provided YAML configuration and the actual output behaviour observed on target.While the model itself appears to perform well, the mapping between output indices and class names does not seem to match the order documented in the YAML file. Observed behaviour:The YAML file lists the classes as:0: dog1: chainsaw2: crackling_fire3: helicopter4: rain5: crying_baby6: clock_tick7: sneezing8: rooster9: sea_waves However, on our target, the outputs appear to correspond to the following order:0: chainsaw1: clock_tick2: crackling_fire3: crying_baby4: dog5: helicopter6: rain7: rooster8: sea_waves9: sneezing This is consistent across multiple input samples, which makes us suspect a systematic label remapping rather than random misclassification. Preliminary hypothesis:We suspect that this could be caused

Hi all,I’m trying to follow this guide here but when I try to run the model on target I always got an error failed to erase memory.Here is the log. I’ve also set external loader from cubeprogrammer to MX66, and if I try to erase memory from cube programmer I also have an error, loose comunication with the boardSaving workspace.[36m[01m -------------------------------------------------------------------[39;49m[0m[36m[01m STM32CubeProgrammer v2.23.0 [39;49m[0m[36m[01m -------------------------------------------------------------------[39;49m[0m[39;49m[0m[90mST-LINK SN : 004700233234510E37333934[39;49m[0m[90mST-LINK FW : V3J17M11[39;49m[0m[90mBoard : STM32N6570-DK[39;49m[0m[90mVoltage : 2.75V[39;49m[0m[90mSWD freq : 8000 KHz[39;49m[0m[90mConnect mode: Under Reset[39;49m[0m[90mReset mode : Hardware reset[39;49m[0m[90mDevice ID : 0x486[39;49m[0m[39;49m[0m[39;49m[0m[39;49m[0m[90mRevision ID : Rev B[39;49m[0m[39;49m[0m[39;49m

Hello expert, I’m using the latest version of stedgeai-dc.st.com (online) to compile my CNN model but by default, choosing the STM32 MCUs, the target is F4 family while I’d compile and optimize my  code for H723ZG board. It seems there is no way to change the target board…. why? and how can I do it? indeed If I see the stdout.txt generated at the end I see:>>> stedgeai generate --model tiny_resistor_cnn.onnx --optimization balanced --target stm32f4 --name network --workspace workspace --output outputST Edge AI Core v4.0.1-20581 7ed50de05so it’s not optimized for my board.Could someone help me please? Many thanks and regardsLorenzo

Subject: YOLOv8n ONNX conversion fails with "region 'ROM' overflowed by 5601536 bytes" on STM32N6570-DKI am trying to convert and generate a YOLOv8n ONNX model for the STM32N6570-DK using STM32Cube AI Studio / ST Edge AI Core.My target configuration is:Board: STM32N6570-DK Accelerator: ST Neural-ART RAM: 4200 KB Internal Flash: 0 KB External RAM: 32 MB External Flash: 128 MB Mode: On targetHowever, the generation fails with the following error:region 'ROM' overflowed by 5601536 bytesSince the STM32N6570-DK has 128 MB of external Flash, I would like to understand why the ROM region overflows and whether the model/data can be placed in external Flash.What memory configuration or settings should I use to deploy YOLOv8n on the STM32N6570-DK?I have attached the complete log and the ONNX model.  YOLOv8n　Data↓https://github.com/ultralytics/assets/releases/download/v8.4.0/yolov8n.pt

Context : I want to write a FSBL load and run application on a custom minimal PCB based on STM32N6-DK design. The board uses SMPS power supply and not the default power supply of the STM32N6-DK. I follow this original tutorial  as a main example. Problem faced: CubeProgrammer SigningTool version compatibility and header size 1) Write a custom external bootloader to write and read external flash memoryModify the power supply parameter (System Core --> RCC --> SupplySource) in CubeMX to `PWR_SMPS_SUPPLY`Generate ExtMemLoader template from CubeMX Build ExtMemLoader to generate .stldr filemake sure the post build script can be executedmanually copy the .stldr file generated in `/STM32CubeProgrammer.app/Contents/Resources/bin/ExternalLoader/` if necessary  2) Modify SigningTool header generation command in FSBL post-build Build FSBL & Application following the original tutorialCheck heading size, it might be different from the 0x400 that is defin

LL_ATON_LIB_Concat falls back to 4× memcpy when the concat axis is not leftmost — 32% of a 4 ms real-time budget on STM32N6Hardware: NUCLEO-N657X0-Q (STM32N657X0H3Q), Cortex-M55 @ 800 MHz, Neural-ART. Tools: ST Edge AI Core 4.0, STM32Cube_FW_N6 V1.4.0, STM32CubeIDE 2.1.1. Application: real-time audio, hop = 192 samples @ 48 kHz = 4 ms = 3.2 M cycles, hard deadline, underrun must stay 0.1. Concat falls back to a byte loop, and it is one third of the budgetOur graph is a streaming TCN (int8, L=12, C=88, T=48) run per audio hop with two voices, so the tensor layout has the voice axis leftmost: [C][V][T]. The graph contains 12 Concat blocks (channel-wise taps).Epoch profiling (LL_ATON_EB_DBG_INFO, DWT cycle counter on the M55) showed those 12 blocks costing 1 019 501 cycles per inference — 32% of our entire 4 ms budget. No compiler option changed the number.The cause is in the runtime source: LL_ATON_LIB_Concat takes its fast DMA path only when the concatenation axis is the leftmost signif

Hi,I was trying to figure out how to use external memory and flash with xcubeai, and I found a video posted by STM32 says there is an example food recognition code in stm32ai-modelzoo-services on Github. However, I couldn't find it. Was it deleted?thanks.

Hi all, Any well defined step by step for STM32N6 disco board? a link would be appreciated.  Thank you. 

HelloST Edge AI: Guide for STM32MPU 、 Section 3.2.1. Referring to “Generate NBG from TensorFlow™ Lite or ONNX,”I converted the .tflite file downloaded from ModelZoo to .nb, but I’m getting an error.$ /opt/ST/STEdgeAI/4.0/Utilities/linux/stedgeai generate -m ./yolov8n_256_quant_pc_uf_od_coco-person-st.tflite --target stm32mp25ST Edge AI Core v4.0.1-20581 7ed50de05E102(CliArgumentError): stm32mp25 not recognized as target. Supported targets areispu --device DEVICEmlcstm32f4stm32l4stm32l4pstm32g4stm32f3stm32wbstm32n6 [--st-neural-art]stm32f0stm32l0stm32g0stm32c0stm32wlstm32v8stm32u3 [--hsp]stm32h7stm32f7stm32u5stm32l5stm32h5stm32c5stm32mp157cIf you change the target name slightly, you'll get the following error: $ /opt/ST/STEdgeAI/4.0/Utilities/linux/stedgeai generate -m ./yolov8n_256_quant_pc_uf_od_coco-person-st.tflite --target stm32mp2ST Edge AI Core v4.0.1-20581 7ed50de05E102(CliArgumentError): stm32mp2 is not availableCould you tell me how to convert a .tflite file to

Hi everyone, I have a N6 Discovery Kit with a camera. Additionally, I have an N6 Nucleo Board. Now I want to use the CubeMX and CubeIDE to capture a frame on the Nucleo with the camera. I copied most of the things from the `DCMIPP_ContinuousMode` example but I still can't get it working...   The I2C communication works (over I2C2) CAM_NRST => GPIO O5 get set to high. CAM_EN => GPIO A0 get set to high. Then I successfully call the IMX335_Probe(..) And finally, it fails here: https://github.com/rphii/NUCLEO_N6_DCMIPP_MB1854B/blob/main/Appli/Core/Src/main.c#L137 (contains the full, minimal, reproducible code) I never get into the `HAL_DCMIPP_PIPE_FrameEventCallback`...   If anyone has more experience with the DCMIPP and CSI-2 (which is both new to me) and could help, it'd be greatly appreciated, thanks!  

This account only shares restored community content posted by members between May 22 and June 9, 2026, who did not register for the new community.Dear ST Community, I'm trying to integrate my ST Edge AI model C code (generated from ST Edge AI Cloud) to my current application.- Part Number: STM32F411CE6- Environment: STM32CubeMX: 6.17; ST Edge AI Core v4.0.0-20500 359356bb0- Detail of my issue:   At line 63 below: huart2.Instance = 0x40004400   After successfully execute stat_network_run() (line 65): huart2.Instance = 0x582cc4de -> This causes Bus Fault to be triggered in line 70.    My main function:   void print_to_uart(UART_HandleTypeDef *huart, const char *format, ...) {char buffer[256];int cx;va_list args;va_start(args, format);cx = vsnprintf(buffer, sizeof(buffer), format, args);va_end(args);if (cx >= 0 && cx < (int)(sizeof(buffer))) {HAL_UART_Transmit(huart, (uint8_t*) buffer, cx, 1000);} }// ...STAI_ALIGNED(STAI_NETWORK_CONTEXT_ALIGNMENT) static stai_network net

Hello, I have just updated STM32CubeAI Studio to version 1.2. In the previous version, the AI Studio generated: Middleware Application code Raw files (e.g., network_atonbuf.xSPI2.raw) My workflow was to add the middleware and application code to my project, then convert the raw file (network_atonbuf.xSPI2.raw) to a hex file. Everything worked fine until I updated the studio. In version 1.2, instead of generating the raw file, it now generates a C source file: network_atonbuf.xSPI2.c. I am unsure what to do with this new .c file. I placed it in my project, but nothing works as expected. Could someone please advise on how to proceed or explain the change in workflow?  

EnvironmentI am trying to deploy a U-Net segmentation model on STM32N6 using ST Edge AI Cloud.ST Edge AI Core:ST Edge AI Core v4.0.1-20581Target:stm32n6Current StatusThe model conversion and quantization steps complete successfully.The workflow is:PyTorch U-Net ↓ONNX FP32 export ✓ successful ↓Per-channel quantization ✓ successful ↓ST Edge AI optimization / Neural-ART compilation ✗ failedTherefore, the issue does not occur during ONNX export or quantization.The failure happens specifically during the Neural-ART optimization/compiler stage.Model ArchitectureInput:[1, 3, 320, 320]Output:[1, 1, 320, 320]The network is a U-Net-like segmentation architecture.Encoder channels:64 → 128 → 256 → 512Bottleneck:1024Decoder channels:512 → 256 → 128 → 64Each convolution block consists of:Conv2D→ BatchNorm→ ReLU→ Conv2D→ BatchNorm→ ReLUDownsampling:MaxPool2Dkernel_size = 2stride = 2Upsampling:ConvTranspose2Dkernel_size = 2stride = 2The encoder feature maps are concatenated with the

Hello,I am trying to create a custom AI model and run inference on the NPU of an STM32MP255F.At the moment, my goal is only to verify the model creation workflow. Therefore, inference accuracy is not important yet.Environment Target device: STM32MP255FInference engine: NPUNumber of training images: 116 (mouse images)Steps1. Dataset creation with RoboflowAnnotated all images. Resized images to 256x256. Exported the dataset in YOLOv8 format.2. Training and export with UltralyticsTraining:yolo detect train data=data.yaml model=yolov8n.pt epochs=100 imgsz=256Export:yolo export model=runs/detect/train/weights/best.pt format=onnx imgsz=256 quantize=8 data=coco83. Conversion with ST Edge AI Developer Cloud Uploaded the exported model to ST Edge AI Developer Cloud. Selected the platform: "STM32 Microprocessors embedding Cortex-A loaded with X-LINUX-AI" Executed Optimize. However, the following error is displayed and no .nb file is generated:Error while generating optimized file. Generation

Built a minimal on-device training stack for STM32 — fits in 608 bytes RAM total.The problem: Adam optimizer needs exp_avg + exp_avg_sq — 2× parameter RAM. On STM32F103 (20KB SRAM) with a 5K parameter model that's 40KB just for optimizer state. Doesn't fit.What I built:GravOptMini — momentum optimizer with quantile-based gradient freeze. Only exp_avg (1× param RAM). Freezes low-gradient parameters to reduce compute.W-Twin Lite — power-law baseline fitted on early steps, tracks deviation. Pure float32, no scipy, no numpy. Rolling window of 20 values. ~240 bytes.Benchmark (Python simulation, STM32 memory constraints):- Model: 46 params, 184 bytes- GravOptMini state: 368 bytes (exp_avg only)- W-Twin Lite: 240 bytes- Total: 608 bytes- MNIST accuracy: 93.2% vs Adam 97.4%- W-Twin overhead: 3.9% per step- Detection: anomaly caught 96 steps before visible loss divergence, 0 false alarms on clean runNext step is a real STM32 test with physical hardware. C port of both components is the plan.Has

Hi,I recently erased the external flash of my STM32N6570-DK board while experimenting with STM32CubeProgrammer, and I'd like to restore the original out-of-the-box demo (the multi-application menu demo with image classification / pose estimation / face detection etc.).I found the "n6-ai-demos" entry under Tools & Software on the product page, but clicking "Get latest" leads to a 404 page not found error.Could someone please:Confirm whether this link is currently broken on ST's side, or Share a direct working link / attach the "STM32N6570-DK Out-of-the-box demo binary" fileBoard info:Board: STM32N6570-DK, Revision ID Rev Z Device ID: 0x486Thanks in advance!  

Hello ST Community,We are currently using the x-cube-n6-ai-face-landmarks pipeline on the STM32N6570-DK. We now want to extend the BlazeFace stage so that it can detect additional DMS-related classes along with face detection. The classes we are interested in are:Phone, Seatbelt, Smoking, Face, Drinking. At present, the BlazeFace model used in the ST face-landmark project is a single-class face detector, and we could not find a public ST training pipeline for retraining or extending this specific BlazeFace model. Is there any ST example or reference repository for training BlazeFace on:WIDER FACE, custom datasets, or custom multi-class datasets?Our goal is ideally to reduce the number of separate detection models while keeping the existing face-landmark pipeline functional on STM32N6570-DK.Any guidance on the recommended training flow, supported model architecture, or available reference code would be very helpful.

I'm currently developing with the STM32N6570-DK, using STM32N6 1.4.0 firmware, and using AI Studio and CubeMX to generate projects.However, I've encountered a very confusing problem. In the program generated by AI Studio, after calling MX_EXTMEM_MANAGER_Init() in the FSBL, it calls functions like BSP_XSPI_NOR_Init() and BSP_XSPI_RAM_Init(). This seems to be an additional Flash and SRAM driver written separately by the official documentation. /* Initialize all configured peripherals */ MX_GPIO_Init(); MX_XSPI1_Init(); MX_XSPI2_Init(); MX_EXTMEM_MANAGER_Init(); /* USER CODE BEGIN 2 */__HAL_RCC_AXISRAM2_MEM_CLK_ENABLE(); __HAL_RCC_AXISRAM3_MEM_CLK_ENABLE(); __HAL_RCC_AXISRAM4_MEM_CLK_ENABLE(); __HAL_RCC_AXISRAM5_MEM_CLK_ENABLE(); __HAL_RCC_AXISRAM6_MEM_CLK_ENABLE();/** Workaround for an issue generated in STM32CubeN6 FW 1.4.0 **/ extern XSPI_NOR_Ctx_t XSPI_Nor_Ctx[XSPI_NOR_INSTANCES_NUMBER];

Hi ST Support Team,We encountered a reproducible HardFault when running an object detection model on the STM32N6570-DK, and have completed extensive isolation testing. We believe this points to an issue in the STEdgeAI 4.0.1 / Neural-ART toolchain combined with the Getting Started reference application (concurrent camera/display/NPU usage), rather than a configuration mistake on our side.[Environment]- Board: STM32N6570-DK (with IMX335 camera)- Project: Getting Started Object Detection App (stm32ai-modelzoo-services)- Model: st_yoloxn (1 class, 416x416), Quantized (input: uint8 / output: int8)- Toolchain: STEdgeAI Developer Cloud v4.0.1 (forced by cloud; v4.0.0 is no longer offered, though the project's own README states the shipped model files were generated with v4.0.0)[Symptom]Build, flash, and boot-from-flash all complete without error, but the LCD stays black. Debugging via STM32CubeIDE shows a HardFault during NPU inference:HardFault_Handler()__LL_ATON_RT_IrqErr(irqs)   // ll_ato

Hello ST Community,I am working with the STM32N6570-DK and running a custom-trained ST YOLOX Nano object detection model using the STM32N6 Getting Started Object Detection application.My custom model has 5 classes.The model is successfully generated and integrated into the STM32N6570-DK object detection project. The application starts correctly, the camera/display starts running, and I can see a few frames initially.However, after processing a few frames, the display freezes/stops updating. The board itself does not appear to continue normal inference after this point.I also noticed an unexpected LED indication on the board. This LED was not active when I previously ran the standard/reference object detection model. I have attached photos of the front and back of the STM32N6570-DK showing the LED state. My setup is:Board: STM32N6570-DK Application: STM32N6 Getting Started Object Detection Model: Custom ST YOLOX Nano Input: 480 x 480 x 3 Number of classes: 5 Camera: ST camera module con

Hello, I recently encountered this error while deploying an AI model on an STM32N647 for performance verification. I noticed that others have encountered the same issue on the official website, but following the suggested solutions did not resolve my problem—I’m still getting the same error. This issue has been troubling me for a week now. Are there any other ways to resolve it? 

Dear ST Edge AI Support Team,We are deploying a YOLO11n person-detection model on the STM32N6 NPU using the relocatable(LRUN) generation flow. While decoding the generated runtime buffer descriptors on-target, wefound that the top-level *input* user-IO buffer's channel-position metadata disagrees with itsown reported memory shape, and does not change when explicitly requesting a channel-last inputlayout.Configuration Target: STM32N6 ST Edge AI Core v4.0.1-20581 7ed50de05 Model: yolo11n_256_quant_pc_uf_od_coco-person-st.tflite (quantized, uint8 input, 256x256x3) stedgeai cli command (as echoed by network_generate_report.txt):   "stedgeai generate --model yolo11n_256_quant_pc_uf_od_coco-person-st.tflite --relocatable    split --target stm32n6 --no-inputs-allocation --no-outputs-allocation --optimization    balanced --st-neural-art user_profile@profile-neural-art.json --name network --verbosity 1    --c-api st-ai --inputs-ch-position chlast --workspace ./workspace --output ./outputs"Issue

I am integrating X-CUBE-AI and the STM32H7 Safety STL into the same STM32H743 Keil/ArmClang project.The X-CUBE-AI Keil runtime requires short enums and 16-bit wchar_t (-fshort-enums -fshort-wchar). However, the Safety STL library appears to require full-size enums and 32-bit wchar_t.Configuring the project for X-CUBE-AI causes the Safety STL library to fail linking. Configuring it for the Safety STL causes Arm linker ABI errors when linking the X-CUBE-AI runtime, including enum-size and wchar_t mismatches.Is there an officially supported compiler configuration or compatible library variant that allows X-CUBE-AI and the STM32H7 Safety STL to coexist in the same ArmClang application?

Hello,I’m using STM32Cube AI Studio to optimize and validate an ONNX model on a NUCLEO-N657X0-Q board. In general, everything works fine. However, I would like the board to be configured in overdrive mode (npu_freq = 1000MHz, mcu_freq = 800MHz) by Cube AI Studio for the validation runs on the target because I’m hoping to achieve a better inference time.When executing new “runs” in Cube AI Studio, the device attributes are always as seen in the screenshot below.Results overview of a run in Cube AI StudioIf I use the the ST developer cloud to optimize and benchmark my model with the STM32N6570-DK board (because the NUCLEO-N657X0-Q is not available in the DC), the device attributes are as follows:Device attributes for the benchmark in the developer cloudSince those two boards have the same STM32N657X0H3Q MCU, I expect a similar inference time on my NUCLEO-N657X0-Q board with Cube AI Studio if I could just activate the overdrive mode. I didn’t find any settings in the Cube AI Studio user i

Somesays ago, I successfully used STM32Cube.AI Studio to deploy a model to an STM32U585CIU6 board and test it.However, yesterday evening I upgraded STM32CubeIDE, STM32CubeProgrammer, and STM32CubeMX. After that, when I tried to run the same process again, I started getting an error.I searched online and found some similar cases. The suggested solution was to update all related software, so I updated the tools accordingly. However, the same error still occurs.I also tried using another laptop. On that laptop, I performed the same software upgrades and then tested with an STM32H743VIT6 board, but the same error occurred there as well.Because of this, I suspect that I may have missed updating some required software or package.Has anyone experienced this issue before or found a solution? I would greatly appreciate any advice or guidance.ps : stedgeai version is v4.0.1.