Edge AI

안녕하세요,현재 STM32N657-DK 와 X-CUBE-AI(ST Edge AI Core v2.2.0)를 사용하고 있습니다 . TensorFlow Lite 모델을 NPU에서 실행되도록 변환했으며, 펌웨어를 성공적으로 빌드하고 플래싱할 수 있습니다.하지만 내가 전화하면: ret = LL_ATON_RT_RunEpochBlock(&NN_Instance_Default);함수가 결코 반환되지 않습니다.내가 이미 구성한 것시계 및 재설정NPU 클럭을 활성화하고 재설정을 해제했습니다. __HAL_RCC_NPU_CLK_ENABLE(); __HAL_RCC_NPU_FORCE_RESET(); __HAL_RCC_NPU_RELEASE_RESET();set_clk_sleep_mode()에서도 슬립 모드 클록이 활성화됩니다.인터럽트 라우팅보안 프로젝트에서: NVIC_DisableIRQ(NPU3_IRQn); NVIC_ClearPendingIRQ(NPU3_IRQn); NVIC_SetTargetState(NPU3_IRQn); // 비보안으로 경로 지정 NonSecure 프로젝트에서: HAL_NVIC_SetPriority(NPU3_IRQn, 0 , 0 ); HAL_NVIC_EnableIRQ(NPU3_IRQn); void NPU3_IRQHandler ( void ) { printf ( ">> NPU IRQ가 실행됨\r\n" ); ATON_STD_IRQHandler(); }RIF / RISAF 구성NPU 마스터/슬레이브 속성을 비보안 + 특권으로 구성했습니다.NonSecure에서 NPU RAM3~RAM6(0x3420_0000~0x343C_0000)에 액세스할 수 있도록 RISAF 구성을 추가했습니다. RISAF_ConfigRegion( 3 , 0x34200000 , 0x70000 , RISAF_ATTR_비보안 | RISAF_ATTR_PRIV); RISAF_ConfigRegion( 4 , 0x34270000 , 0x70000 , RISA

Hello,I want to run my own neural network on a NUCLEO-F722ZE board for classifying audio samples. Since there is an older existing example project by STM (Acoustic Scene Classification) so I kept the whole data structure quite similar to this project, using the same network topology and same input vector size.I loaded my keras .h5 file into X-CUBE-AI and was able to successfully analyze the model and generate code. After this I followed the instructions in the arcticle "How to perform motion sensing on STM32L4 IoTnode" and implemented two functions identical to the AI_Init() and AI_Run() and the respective variables. I am able to successfully initialize and create the AI model, with the ai_network_1_create_and_init() function returning 0 and the network handle being not null (my given network name is "network_1") . After this I fill the input array with data and call the AI_Run() function, which then again calls my ai_network_1_run() function, which again calls the ai_pl

Hi,I would like to check if there is any one who could guide me through the jungle of using TFLM in my software. It seems that it don't matter what I do when building a TFLM as a static library and link it to my simple test program. I have tried a lot of configurations and a lot of tries to 16 byte align the model and arena for this, but I am still getting a hard fault because of unaligned access in the AllocateTensors call.My align of the model looks like this:alignas(16) const unsigned char g_model_data[] = ...and my code using TFLM looks as follows:#include <cstring> //#include "tensorflow/lite/micro/micro_op_resolver.h" #include "tensorflow/lite/micro/micro_mutable_op_resolver.h" //#include "tensorflow/lite/micro/kernels/micro_ops.h" //#include "tensorflow/lite/micro/micro_log.h" //#include "tensorflow/lite/micro/micro_error_reporter.h" #include "tensorflow/lite/micro/micro_interpreter.h" #include "tensorflow/lite/schema/schema_generated.h" #include "tensorflow/lite/micro/sy

Now, i used yolo11 module ,cd /opt/ST/STEdgeAI/2.2/Utilities/linux/./stedgeai generate -m /home/alientek/STM32MPU_workspace/yolo11.onnx  --target stm32mp25and get yolo11.nb file in the my stm32mp2 broad.x-linux-ai-benchmark -m ./yolo11n.nb╔════════════════════════════════════════════════╗║ X-LINUX-AI unified NN model benchmark ║╠════════════════════════════════╦═══════════════╣║ Machine ║ STM32MP257 ║║ CPU cores ║ 2 ║║ CPU Clock frequency ║ 1.5GHz ║║ GPU/NPU Driver Version ║ 6.4.19 ║║ GPU/NPU Clock frequency ║ 800 MHZ ║║ X-LINUX-AI Version ║ v6.0.0 ║║ ║ ║║ ║ ║╚════════════════════════════════╩═══════════════╝For hardware accelerated models, computation engine used for benchmark is NPU running at 800 MHZFor other models, computation engine uses for benchmark is CPU with 2 cores at : 1.5GHz╔══════════════════════════════════════════════════════════════════════════╗║ NBG models benchmark ║╠════════════╦═════════════════════╦═══════╦═══════╦═══════╦═══════════════╣║ Model Name ║

Hello everyone,I'm working on a project in STM32CubeIDE and I'm trying to include the CMSIS-DSP math library. During the build process, I'm running into a linker error and can't figure out what's wrong with my settings.The error message is ld.exe: cannot find -llibarm_cortexM4l_math.a: No such file or directory.I have added the path to the library in MCU GCC Linker > Libraries > Library search path (-L). I've also double-checked that the library file libarm_cortexM4l_math.a does exist in that path. I suspect the issue is how I'm specifying the library itself.Here is the full command and error from the build console:arm-none-eabi-gcc -o "stm_niso_watch_fw2_TEST.elf" @"objects.list" -llibarm_cortexM4l_math.a -mcpu=cortex-m4 -T"C:\Users\vishv\Downloads\STM32_AI\stm_niso_watch_fw2_TEST\STM32WB5MMGHX_FLASH.ld" --specs=nosys.specs -Wl,-Map="stm_niso_watch_fw2_TEST.map" -Wl,--gc-sections -static -L"C:\Users\vishv\Downloads\CMSIS_4-master\CMSIS_4-master\CMSIS\Lib\GCC" -L"C:\Users\vishv\D

Hello,I am following this tutorial:https://community.st.com/t5/stm32-mcus/how-to-build-an-ai-application-from-scratch-on-the-nucleo-n657x0/ta-p/828502After completing step 4.3 Build, I encountered linker errors when compiling the TUTO_N6_MINIMAL_AI_Appli project.Here is part of the build log:./Middlewares/ST/AI/Npu/ll_aton/ll_sw_integer.o: in function `ll_sw_forward_dequantizelinear':... undefined reference to `node_convert'./Middlewares/ST/AI/Npu/ll_aton/ll_sw_integer.o: in function `ll_sw_forward_softmax_integer':... undefined reference to `forward_sm_integer'./Middlewares/ST/AI/Npu/ll_aton/ll_sw_integer.o: in function `ll_sw_forward_resize_integer':... undefined reference to `forward_resize_nearest_is8os8'... undefined reference to `forward_resize_bilinear_is8os8'... undefined reference to `forward_upsample_zeros'My environment:STM32CubeIDE 1.19.0CubeMX 6.15.0X-CUBE-AI package (latest, bundled with CubeMX)Board: NUCLEO-N657X0Example: TUTO_N6_MINIMAL_AI (as in tutorial)Question:Is th

Hi Chris @Chris_Young_ST, Giuseppe @gpagano, Emmanuel @Emmanuel_C and Kunliang @Kunliang_YAOAre there plans to offer ST image sensors together with the STM32MP257F-DK and STM32N6570-D development boards as an alternative to the Sony image sensor in the B-CAMS-IMX board?ST has an enormously strong strategic position through its global leadership in producing both image sensors and processors. This will allow ST customers to achieve unparalleled speed, efficiency and sustainability together with rapid route to market in demanding power-sensitive and low-latency machine vision and EdgeAi applications.Our focus is on developing technologies for conservation of Europe's most beautiful and endangered dormouse, squirrel and bat species. The combination of ultra-low-power Edge AI capabilities in the STM32N657 μC and the advanced RGB-IR capabilities in ST image sensors is as exciting here as it is in the most demanding commercial machine vision applications:ht

Hello,I am trying to use miniresnet provided at [miniresnet] on B-U585I-IOT02A board.I am using STM32CubeIDE locally, following the instruction from [wiki] for setting up software environment, and from [configuration] and [deployment] documentation for configuration and deployment. I generated the C code using the CLI and am viewing inference results via the Serial Monitor.However, when I run inference, I encounter an error with code -4.It appears to come from the following condition "NbrOfBytes > 65535U" in "./STM32Cube/Projects/stm32ai-modelzoo-services/application_code/sensing_free_rtos/STM32U5/Drivers/BSP/B-U585I-IOT02A/b_u585i_iot02a_audio.c".int32_t BSP_AUDIO_IN_Record(uint32_t Instance, uint8_t *pData, uint32_t NbrOfBytes) { int32_t status = BSP_ERROR_NONE; if ((Instance >= AUDIO_IN_INSTANCES_NBR) || (pData == NULL) || (NbrOfBytes > 65535U)) { status = BSP_ERROR_WRONG_PARAM; } ...In my case, NbrOfBytes is calculated to be 66816, which

https://community.st.com/t5/stm32-mcus/how-to-build-an-ai-application-from-scratch-on-the-nucleo-n657x0/ta-p/828502There was a problem while following this guide.In dev mode, the signed binary files are programmed in cubeprogrammer and re-run in flash mode, and the blue light remains on. (The FSBL main() runs normally)I set BOOT_Application() to breakpoint through CUBEIDE and debugged line by line.An error occurred in img_size = BOOT_GetApplicationSize(uint32_t) source for CopyApplicationsource:<error: Cannot access memory at address 0x70100000>destination:<error: Cannot access memory at address 0x24050000>I have confirmed that there is an error.0x70100000 I programmed the signed application file in that areaWhat is the reason for this problem?

Hi,In STM32N6570-DK_GettingStarted_ObjectDetection project when I add another uint8 model it is stopping at app_postprocess_od_st_yolox_ui.c and it is moving to hard fault 1. I am unable to start with camera in my new project. So I am using STM32N6570-DK_GettingStarted_ObjectDetection project to deploy customising model. but when I quantise the model using CLI, I am unable to run the code it is going to hard fault. 

Can I use MMAction2 with TSN or SlowFast behavior recognition models and deploy them to the STM32MP257? Does the STM32MP257 support 3D CONV operators?

The examples/code snippets found in the ST Edge AI Core Technology Documentation (ST Edge AI Core Technology 2.2.0) show a variety of functions/macros used that don't seem to get generated via STM32CubeMX on my end.For reference, I generated the code for CMake, with version 10.2.0 of X-Cube-AI and 6.13.0 of STM32CubeMX.A couple examples from the legacy client -> new edge ai embedded client migration guide:#include "network_inputs.h" - No such file <model_name>_inputs.h seems to get generated via CubeMX.STAI_NETWORK_CONTEXT_DECLARE - this macro is undeclared in the generated code.stai_network_init() - I get an implicit declaration of function warning for this one (cannot find this declared/defined anywhere in the generated code).STAI_NETWORK_ACTIVATIONS_NUM - also undeclared in generated code. Is this specific to the code generated for CMake? Are there perhaps other header files I should be looking to include aside form the ones noted in the examples? EDIT: Confirmed

Hey,Looking at the image classification application example, I couldn't find any part of the code that handles the normalization of pixel value from [0,255] to [-1,1] or [0,1] that I would expect from a CV model of that kind. Do you mind explaining how this implementation that is based on the mobilenet_v2_0 skips the need for normalization?Thanks. 

Hello,I'm trying to convert my keras model for STM32N6. CubeMX Version: 6.15.0X-Cube-ai Version: 10.2.0The code for my model:img_input = Input(shape=(10, 141, 141, 3), name='img_input') # --- CNN branch applied per-frame via TimeDistributed --- cx = layers.TimeDistributed(layers.Conv2D(16, (3, 3), activation="relu"), name="CNN_Conv1")(img_input) cx = layers.TimeDistributed(layers.BatchNormalization(), name="CNN_Batch_Norm")(cx) cx = layers.TimeDistributed(layers.MaxPooling2D(2, 2), name="CNN_Pool1")(cx) cx = layers.TimeDistributed(layers.Conv2D(32, (3, 3), activation="relu"), name="CNN_Conv2")(cx) cx = layers.TimeDistributed(layers.MaxPooling2D(2, 2), name="CNN_Pool2")(cx) cx = layers.TimeDistributed(layers.Conv2D(64, (3, 3), activation='relu'), name="CNN_Conv3")(cx) cx = layers.TimeDistributed(layers.MaxPooling2D(2, 2), name="CNN_Pool3")(cx) cx = layers.TimeDistributed(layers.Flatten(), name="CNN_Flatten")(cx) cx = layers.TimeDistributed(layers.Dense(128, activation='relu'),

I am working on a project where I am required to deploy a Neural network on STM32 Nucleo- H755ZIQ. And I feel stuck because I am unable to properly run it on the board using Stm32CubeIDE with X cube ai. I downloaded the .ioc file and the project files from ST Edge AI Developer Cloud but I could'nt figure out how to properly flash it on the board and verify it. I also cant seem to figure out the clock configuration, usart, and I dont know how to access a serial monitor on mac. I have .csv files to test the model on the board, but I cant figure out where to insert the file for testing. I tried using Simulink hoping it'll be easier but the stm32 hardware support package is not supported on MacOS(M1). Can anyone help me out figuring out the pipeline to deploy this model? I am fairly new to stm32 MCUs and have limited experience in embedded.It is a Keras model which takes in ECG data in string arrays and classifies it. Right now I am only feeding the model with .csv file

Hello, I installed X-CUBE-AI 10.2.0 from STM32CubeMX in STM32CubeIDE 1.18.1. After enabling X-CUBE-AI in the ioc file and performing code generation, the folders /Middlewares/ST/X-CUBE-AI/Inc and /Middlewares/ST/X-CUBE-AI/Lib are created, but no code is generated in those folders. Therefore, when building the project, I get an error such as:fatal error: ai_platform.h: No such file or directoryIn Project Manager → Code Generator → Generated files panel, I unchecked the option “Delete the previously generated files when not regenerated” and regenerated the code, but the problem was not solved. Please help me.If there is any necessary information that I have not provided, please let me know.This message was translated into English using generative AI. I apologize for any awkward sentences or expressions.Thank you.

Hello - I'm quite new to the world of ML and machine learning on embedded and I'm having trouble implementing a model I've trained on the board. It is a hand gesture recognition model and the point was for me to understand the whole ML development process by training and deploying a model from scratch. I have been referencing this article: How to build an AI application from scratch on the... - STMicroelectronics Community and have followed all the steps. I tried once using a model from the model zoo and it worked fine but when trying with my own model it hits a hardfault and halts execution - so I'm guessing it is an issue with my model. I've attached a zip file of my project and a zip of the notebook file and exported model (i actually ended up uploading the keras model to ai developer cloud and quantising/optimising the model in there, so ignore this part in the notebook).Another issue I've been having lately is regeneration of code with cube mx - I generate code for the f

RAM Overflow and X-CUBE-AI Quantization Analysis Error with PyTorch Model on STM32F401REHello everyone,I'm working on deploying a PyTorch model to an STM32F401RE NUCLEO board and encountering some challenging memory and quantization issues that I hope the community can help me resolve.Project ContextMy project involves running a custom PyTorch model (converted to ONNX format) on the STM32F401RE NUCLEO board. The system already has USB Host (Audio Class) library and FreeRTOS integrated as essential components for my application, which means I need to work within the remaining available memory space.Development EnvironmentBoard: STM32F401RE NUCLEO (96KB SRAM)IDE: STM32CubeIDE 1.18.1X-CUBE-AI: 10.2.0Additional Libraries: USB Host (Audio Class), FreeRTOSModel: PyTorch → ONNX convertedProblem 1: RAM Overflow During BuildWhen I configure X-CUBE-AI with compression set to high and optimization set to ram, the build process fails with a linker error:C:/ST/STM32CubeIDE_1.18.1/STM32CubeIDE/plugi

Hello,I’ve been working on a project inspired by STMicroelectronics project, where the goal is to identify different operation modes of a power drill — such as drilling, screwing, and idle — using motion sensor data.I’m using one of ST’s development kits (e.g., STEVAL-STWINKT1B) and built my classification model using NanoEdge AI Studio.System Overview:Data Collection:I collected 20 signal recordings per class, each consisting of approximately 200 rows of sensor data.Sensor Preprocessing:The raw data from the accelerometer and gyroscope is passed through multiple filters to improve signal quality:Low-pass filterMoving average filterKalman filterDecision Mechanism (Sliding Window + Majority Voting):To improve classification stability in real-time, I implemented a sliding window with majority voting strategy:A buffer stores the last 50 predictions from the model.If at least 40 out of 50 predictions belong to the same class, that class is accepted as the current state.This helps prevent n

Hello,I am creating a new project on an STM32F4 nucleo board. I configured the X-CUBE-AI library as shown below and specified a TFLite model:When generating code on a fresh project, the "Middlewares" folder is not generated. The project fails to build because the "ai_platform.h" file is missing (it should be in the Middlewares folder). The problem occurs with a fresh STMCubeIDE project and with a fresh STMCubeMX project.I noticed that the "Middlewares" folder is generated correctly once I add additional libraries, such as FreeRTOS. In this case, both the FreeRTOS and the X-CUBE-AI code is generated correctly in the "Middlewares" folder. However, I don't want an RTOS for my application.How can I only generate the code for X-CUBE-AI?Best regards,kahuna

Hello,I have been conducting research for a while for a new project initiation. The project aims to design a smart access control system for 500 users using STM32. In designing this, we are implementing face recognition with FP_AI_FACEREC in the STM32H7 series and creating the display design with touchGFX. I have made progress in the project, and by adjusting the RAM settings of the face recognition library, I was able to accommodate 500 users. However, the library doesn't work at the desired accuracy level, especially when similar users are enrolled after reaching 50 users. It sometimes mistakenly identifies a user and allows access. This has raised doubts about the use of the H7 series, and I am considering selecting an MP135 series card for the processor. If someone is knowledgeable about this, could they provide information about the performance of the H7 and MP135 series for AI? Can we use higher accuracy models if we switch to MP135, or would we achieve similar performance as wit

 I've implemented a multi-model face recognition system on the STM32N6 (originally based on the single model object detection demo) that efficiently runs detection and recognition models simultaneously on the NPU. Sharing the complete implementation since deploying and managing multiple AI models on the hardware has some non-obvious challenges.Detection Model: CenterFace for face detection (9ms inference)Recognition Model: MobileFaceNet (130ms per face)Pipeline Management: Efficient switching between models on the NPUAutomated Deployment: Script that takes model paths, names, and addresses as JSON elements and builds + flashes them automaticallyRepository: https://github.com/PeleAB/STM32N6-FaceRecognitionNext steps include creating an abstraction layer for JPEG and H264 compression to handle video streams more efficiently.Happy to discuss multi-model deployment strategies or NPU optimization approaches. The automated build system alone might save others significant setup time.

Hi everyone,I’m trying to deploy a wav2vec model using STM32Cube.AI and ran into an issue during onnx conversion.NOT IMPLEMENTED: Unsupported layer types: LayerNormalizationI’ve read the documentation at supported onnx operators and it seems that LayerNormalization is not currently supported.I have a couple of questions:Are there plans to support LayerNormalization in future releases?If not, does anyone know a recommended workaround other than just modifying the model to use another type of normalization? 

Hi,I have got a TFlite model with s16 activations and s8 weights.1. Without NPU. I run this commandstedgeai.exe generate --target stm32n6 --name network -m %1 --compression none --verbosity 1 -O time --output ./X-CUBE-AIand the utility produces a network with "float" activations and weights (and adding int -> float at the start, and float -> int at the end).Can I use some command line options to force the utility to generate "integer" layers?2. With NPU. I run this commandstedgeai.exe generate --target stm32n6 --st-neural-art n6-noextmem@C:/Users/asdfg/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/10.2.0/scripts/N6_scripts/user_neuralart.json --name network -m %1 --compression none --verbosity 1 -O time --output ./X-CUBE-AI_NPU/Appand the utility outputs the error "NOT IMPLEMENTED: Unkonwn layer format for layer Input_0"With NPU, is it possible to use int16x8 TFlite models?Regards! 

Hey,I have created a simple computer vision NN model and successfully deployed it on my STM32N6570-DK (original and quantized in the zip file).I want to "push" image files (to "emulate" the camera) from my computer to the board to run inference of the images on the board and get classification results and other information if possible.What is the quickest way to do that? Thanks in advance.