Edge AI

In file included from Middlewares/ST/AI/Misc/Src/ai_device_adaptor.c:19:Middlewares/ST/AI/Misc/Inc/ai_device_adaptor.h:655:8: error: unknown type name 'UART_HandleTypeDef'; did you mean 'DMA_HandleTypeDef'?  655 | extern UART_HandleTypeDef UartHandle;      |        ^~~~~~~~~~~~~~~~~~      |        DMA_HandleTypeDefMiddlewares/ST/AI/Misc/Inc/ai_device_adaptor.h: In function 'port_io_get':Middlewares/ST/AI/Misc/Inc/ai_device_adaptor.h:664:12: error: implicit declaration of function 'HAL_UART_Receive' [-Wimplicit-function-declaration]  664 |   status = HAL_UART_Receive(&UartHandle, (uint8_t *)c, 1, timeout);      |            ^~~~~~~~~~~~~~~~Middlewares/ST/AI/Misc/Inc/ai_device_adaptor.h: In function 'port_io_write':Middlewares/ST/AI/Misc/Inc/ai_device_adaptor.h:676:12: error: implicit declaration of function 'HAL_UART_Transmit' [-Wimplicit-function-declaration]  676 |   status = HAL_UART_Transmit(&UartHandle, buff, count, HAL_MAX_DELAY);      |            ^~~~~~~~~~~~~~~~~make: *

Hi ST Community,I am working with an STM32N657 and would like to use the integrated NPU directly from my own C/C++ application.I understand that X-CUBE-AI together with the Neural-ART can generate the code required to execute a neural-network model on the STM32N6 NPU.However, I would like to understand whether it is possible to use the NPU without X-CUBE-AI.Does STM32CubeIde provide HAL APIs that allow an application to directly initialize, configure, load, and start the STM32N6 NPU?

 Hello everyone,I am encountering errors when running Semantic Segmentation, Object Detection, and Pose Estimation models on my STM32N6570-DK board using STM32 Model Zoo Services. Here are the details of my setup and the errors I am facing:Hardware and Versions:Board: STM32N6570-DKModels: Semantic Segmentation, Object Detection, Pose EstimationTools: STM32Cube.AI 4.0.0, GCC 14.3.1, HAL 1.3.0, STMCubeIDE 2.1.1I followed the README instructions from the STM32 Model Zoo Services repository to test the mentioned models. I compiled and flashed the firmware onto the STM32N6570-DK board.Errors Encountered: plaintextCopyBus interface interrupt BUSIF0 ERR: 0x0 BUSIF1 ERR: 0x20 Epoch Controller ERROR interrupt: EC_IRQ = 0x0000000a Epoch Controller opcode counter: 0x00000000 Epoch Controller label: 0x00000000 ATON_STD_IRQHandler()@871: irqs=0xlx assertion "0" failed: file "[...]/stm32ai-modelzoo-services/application_code/.../ll_aton_runtime.c", line 875, function: __LL_ATON_RT_IrqErr&nb

hey i am struggling to flash by custom onnx model on stm32N6570-DK . I tired using the stm32 cube ai cloud website but it only gives me option to generate c code and not a project or elf file . So i shifted to stm32cube Ai studio but it keeps me throwing this error -  (*) 'input'/'output' buffers are allocated in the activations bufferRunning the ONNX model...Running the ST.AI c-model (AI RUNNER)...(name=network, mode=TARGET)E200(ValidationError): TARGET: Unable to bind the ST.AI runtime with "network" c-model: [] E801(HwIOError): Invalid firmware - COM3:115200 can anyone help me to get started with the same

Hi ST Community, I am trying to deploy a YOLO-FastestV2 INT8 object detection model on the STM32N6570-DK. The model is successfully converted and runs on the board, but I am facing issues with the detection results.Model InformationModel: YOLO-FastestV2 (INT8) Number of classes: 6 Parameters: 235,120Model InputInput_0_out_0uint8 [1,1,320,320]Model OutputsQuantize_297_out_0int8 [1,12,20,20]Quantize_313_out_0int8 [1,3,20,20]Quantize_311_out_0int8 [1,6,20,20]Quantize_330_out_0int8 [1,12,10,10]Quantize_346_out_0int8 [1,3,10,10]Quantize_344_out_0int8 [1,6,10,10]Issues I am FacingThe bounding boxes are not displayed at the correct positions on the camera image. The detected bounding boxes appear to be shifted or incorrectly scaled. Even when the camera is not viewing any object (or the camera feed is unclear), random bounding boxes continue to be displayed. These false detection remain on the screen even though there should be no valid detection.Verification PerformedI also tested the quanti

Hi,I am working on a project using STM32H743ZITx and trying to deploy an ONNX model using X-CUBE-AI.My .ld file was doing just fine until I add the X-CUBE-AI in the middleware. It will split the BSS range across DTCMRAM and AXI‑RAM. The startup file’s BSS‑zeroing logic accesses invalid non‑hardware‑backed addresses between the two RAM regions and results in a HardFault right after Reset_Handler.My configuration is:MCU: STM32H743ZITx STM32CubeMX: 6.18.0 STM32Cube FW_H7: 1.13.0 STM32CubeIDE for Visual Studio Code: 3.9.0 Enabled X‑CUBE‑AI 10.2.1Files before and after the configuration of X-CUBE-AI are attached.

Hi all,i have a small question about Validation of a trained model.Atm i only work on PC with NEAI Studio Version 5.1.1.I used only data out of a *.csv fileI trained (benchmark) the model with around 170 Lines and 16 axis to get an accuracy of ~97%.I then validated the library with some test data with same axis count and data preparation. The learning file has the minimum amount of lines as suggested from the benchmark, i tried more lines with same result.The validation shows that even good data is treated as abnomaly so i only get an accuracy of max. 50%.Are there any hints what i am doing wrong? Many thanks in advance for answers.BR’sMartin

I am trying to generate a program a run using STM32Cube AI Studio and the STM32N6570-Dev Kit, but am running into an issue with the run failing due to a resource busy or locked (the .cproject).  Some steps I’ve already taken:Closed all other STM programs (IDE, Programmer, MX) Completely deleted and made a new project Confirmed all ST programs (IDE, Programmer, MX) are up to date by cleaning and re-installing from ST website Confirmed all ST programs are linked to the AI Studio and confirmed they’re all downloaded in their default location. Restarted my PC.Notes:I am on Windows 11, Version 10.0.26200 Build 26200 Model = ST YOLO-X Nano - Person Detection. Source: Pre-trained model from ST Model Zoo Path: stm32ai-modelzoo/object_detection/st_yoloxn/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yoloxn_d033_w025_256/

STM32N657 / STEdgeAI 4.0.1 - Non-deterministic inference results with a minimal STAI wrapperHello,I am currently evaluating STEdgeAI 4.0.1 on an STM32N657 before integrating AI support into my RTOS (uKOS-X).My objective is not to use the generated CubeMX application. Instead, I want to build a small self-contained library that encapsulates all ST Edge AI resources and exposes only a minimal API to the application.The wrapper API is intentionally very small:gan_npu_status_t npu_init(void);gan_npu_status_t npu_putInput(const void *input);gan_npu_status_t npu_inference(void);gan_npu_status_t npu_getOutput(void *output);The application never accesses any STAI object directly.This is only a first validation step, therefore I intentionally use synchronous execution (STAI_MODE_SYNC) and polling only. Interrupt-driven execution will be implemented later.Configuration STM32N657 STEdgeAI 4.0.1 Neural-ART generated network Single network instance ST-generated sources left completely uncha

I would like to clarify the data constraints for Benchmark workflow in NanoEdge AI Studio:What is the maximum supported number of lines for each imported CSV dataset during Benchmark?Is there any official documented hard limit on the number of rows, or only practical recommendations?Some community references mention a rough threshold of ~100,000 lines, and files exceeding this size may cause memory overflow, import truncation or failed Benchmark launch. Could you confirm whether this threshold is formally defined?

Hello ST Community, I noticed that when using the benchmarking tool, datasets larger than 250 MB are automatically reduced using a "representative sampling strategy" that preserves the diversity and distribution of the original data. I would like to understand more details about this process: 1. What specific sampling algorithm/strategy is used? (e.g., random sampling,    stratified sampling, systematic sampling, etc.) 2. How is the target size of 250 MB determined? Is this configurable? 3. How does the tool ensure that the sampled dataset preserves:   - The original data distribution?   - The diversity of data samples?   - Edge cases and boundary values? 4. After optimization, when we validate the model on the full dataset, what    performance differences should we typically expect between the sampled    dataset and the full dataset? 5. Is there any documentation that describes this sampling mechanism in detail? Any information or pointers to relevant documentation would be greatly ap

how can we go initial stm32N6?

hi all, I am trying to flash + run a relocatable / runtime loadable model. The problem is that the inference results are wrong (they never change, no matter what the buffer contains when I start the inference). If I use the stai_model files from the AI Cube Studio, the model works correctly, but is not relocatable… Am aware of matching the address where I flash the network_rel.bin and generating the model. (← see URL) I am using these docs. (← see URL) I am enabling all AXISRAM3...6 I generate the model as follows:stedgeai.exe generate -m "path/to/model.tflite" --input-data-type uint8 --no-inputs-allocation --no-outputs-allocation --target stm32n6 --st-neural-art --reloc# final output something like this:+--------------------------+-------------------------------+------+------------+--------+| name (addr) | flags | foff | dst | size |+--------------------------+-------------------------------+------+------------+--------+| xSPI2 (0x20009332

I am using seeed studio AI assistant board and I am not able generate the cube  project using StudioI am facing Memory Overflow Issue Is there any way to solve thisAnd Seeed Board is not supported when Board is selected during project creation 

I’m trying to convert an ONNX model which has a Conv layer that takes weights as input (has 2 inputs). Edge AI gives me:NOT IMPLEMENTED: Convolution with multiple not constant inputs not supportedAre there any short-term plans to support such layers in ST Edge AI?I also tried to change the name of the layer to some custom name (DynConv). The error in ST Edge AI changed to:NOT IMPLEMENTED: Unsupported layer types: DynConvI thought that I could bypass this error by using --custom with a JSON definition, but the JSON format is poorly documented. Also, many attempts at different formats seem to indicate that --custom only works for Keras. Is this correct?

Hi ST Community,I am working on the STM32N6570-DK board and need guidance on running two AI models together in a single pipeline:YOLO-FastestV2 for object detection (this is my custom train model) MediaPipe Face Landmark for facial landmark detectionMy GoalI want to:Run YOLO-FastestV2 to detect objects/faces from camera input Then run MediaPipe Face Landmark on detected face regions (ROI) Process both models efficiently on STM32N6570-DK Display final output with bounding boxes + face landmarksCurrent StatusI can run object detection examples on STM32N6570-DK. I have AI models available in ONNX/TFLite format. I am exploring deployment using STM32Cube.AI / ST AI tools. I am not sure about the best architecture for running both models together.QuestionsI need help with the following:Is it possible to run two AI models in parallel on STM32N6570-DK? What is the recommended pipeline? Camera → YOLO-FastestV2 → ROI extraction → Face Landmark → Display Output Should both models be merged into

Hi ST Community,I need help regarding a version mismatch issue while deploying my AI model on STM32N6570-DK.Current EnvironmentI am currently using:ST Edge AI Core: v2.2.0-20266 (2adc00962) STM32Cube.AI: 10.2.0-RC1ProblemWhen I convert/generate my model using the current tools, the generated model version becomes:Generated model version: 1.1.3dev14But my board/application runtime is using:Runtime version: 1.1.3dev8Because of this version mismatch, I am unable to run the model properly.My UnderstandingI think I currently have two possible options:Option 1Install an older ST Edge AI version / STM32CubeAI version that generates a model compatible with:1.1.3dev8Option 2Upgrade my runtime/environment on the board so that runtime version becomes:1.1.3dev14QuestionsI need guidance on the following:Which option is recommended by ST? Where can I find the correct ST Edge AI / STM32CubeAI version that generates models for runtime 1.1.3dev8? How can I upgrade the runtime on STM32N6570-DK from 1.1.

I am working on STM32N6570-DK. If I want to deploy random forest model on this MCU, what is the procedure. As most of the time I was using STM32 Cube AI studio to generate IDE project and work on it . But , AI studio doesn’t support tree based models. So, what is the standard procedure for deploying random forest or tree based models on this MCU for real time detection ?  Kindly guideThanks & RegardsChanchal 

Trained Yolov8n on the coco text dataset, trying to import into STCube AI Studio and receive the following error message.Run failed: Error: analyze error: INTERNAL ERROR: 0 vs. 11. Please check the report for more details. Output: ST Edge AI Core v4.0.0-20500 359356bb0 

Hello, I am working on a visual inertial odometry system. It basically contains a camera, a vision processing unit and an IMU. For vision processing part I was thinking of the STM32N6. Can you elaborate on the performance of the ST Neural-ART processsor? Can you elaborate on the inference time? How many images per second can it process?

Hi everyone,I'm deploying a model on the NUCLEO‑H563ZI using NanoEdge AI Studio (v5.2.0). My full training dataset is about 2 GB, and I cannot downsample or reduce features – I must use the complete dataset.My PC specs:- CPU: 12th Gen Intel i7‑12700 @ 2.10 GHz (16 cores total)- RAM: 32 GB (31.7 GB usable)- Storage: 1.82 TB HDD (mechanical drive, WDC WD20EZBX‑00AYRA0)- OS: Windows 64‑bit- Cores allocated to benchmark: 16 (all available)In a previous test with only 40 MB of data, the benchmark took 40 hours on this same machine. If time scaled linearly, 2 GB would take ~2000 hours – impossible for our schedule.Since I cannot change the dataset itself, I'm looking for practical ways to reduce benchmark time through external measures. Specifically, I would like to know:1. Storage bottleneck – My dataset resides on an HDD. Would moving the entire NEAI workspace and dataset to a fast NVMe SSD (or even a RAM disk) dramatically cut the time? Does NEAI repeatedly read from disk during benchmark

 I am an STM32 developer.I recently started studying AI, but unfortunately, I discovered that there is no version of STM32Cube AI Studio for Mac. The same applies to Edge AI Studio. Are there any plans to release a version for Mac?

Please suggest abot EDGE AI 

HardwareBoard: NUCLEO‑U5A5ZJ‑QMCU: STM32U5A5ST‑LINKSoftware / ToolsST Edge AI (via STM32CubeAI Studio)Target: STM32U5Model source: STM32 AI Model ZooModel used:miniresnetv2_s1_64x50_tl_int8.tflite(Audio Event Classification → ESC‑10)Steps FollowedImported the miniresnetv2_s1_64x50_tl_int8.tflite model into STM32CubeAI StudioSelected NUCLEO‑U5A5ZJ‑Q as the target boardKept default settings in all stepsRun on Target Generated code, built, flashed, and attempted (Step 4 – Validate) failed Observed IssueDuring Run on Target, validation fails with the following error:Run failed: Error: validate error: E200 (ValidationError): TARGET: Unable to bind the ST.AI runtime with "network" c-model E801 (HwIOError): Invalid firmware - COM8:115200I have attached the complete validation failure log for reference.Additional ObservationDuring Step 1 (Code Generation), I consistently receive the following warning from STM32CubeMX:Warning: Code GenerationMain Config: These peripherals still have some n

Hi,I have build a custom model based on st yolox model.This model have an input of 480x480. Intput int8 and output float.Five classes for vehicles detectionQuantized and tested on stm32N6570-DK.Now i'm trying to add my model on this st examplehttps://github.com/STMicroelectronics/STM32N6-GettingStarted-ObjectDetection/tree/mainI'm following this tutorial to deploy my modelhttps://github.com/STMicroelectronics/STM32N6-GettingStarted-ObjectDetection/blob/main/README.md#application-build-and-run---dev-modeI'm using stm32cubdeIDE to program the cardAfter i programmed the network_data.hex, i'm trying to deploy and debug the application.But i have this error at this step : app_postprocess_initThe parameters Do you have en idea how i can resolve this ?