Hello,
I have been trying for several weeks to run the Getting Started Object Detection demo from the STM32 GitHub repository.
I followed both the GitHub and all the steps from the official guide:
“How to run AI models from model zoo on STM32N6” by @B.Montanari (ST Employee)— but the STM32CubeIDE part does not work for me.
Each time I try to open the Debug Configuration or start the debugger, I get the following error:
An error has occurred. See error log for more details.
Range [0, -1] out of bounds for length 44
I saw that @Ghofrane GSOURI (ST Employee) suggested removing this line from the .project file:
<nature>com.st.stm32cube.ide.mcu.MCUAppSProjectNature</natureAfter doing that, I can open the Debug Configuration and start debugging,
but when I upload the project to my STM32N6570-DK board, the demo doesn’t run properly(black screen or the ia doesn't work).
Here is what I have already tried:
Following the full official STM32 AI / Model Zoo setup guide step by step
Using different STM32CubeIDE versions (1.17.0, 1.19.0 etc.)
Testing multiple AI models
Reimporting and rebuilding the project
Switching workspaces and reinstalling the IDE,.metadata deleting,
Unfortunately, the issue persists — I can’t successfully debug or run any of the models.
Since I’m currently working on a school project, I really need to get this demo running to continue my work.
Could someone from ST or the community please help me solve this problem?
Thank you very much for your support.
Best regards, xoxo
Abdalla
1 ACCEPTED SOLUTION
Accepted Solutions
Hi @Goat_abdalla,
I tried your object_detection_all_project and successfully ran it.
I had to delete the /debug, build the project and then delete the debug configuration.
I never encountered the range error.
Please try what I did, we never know, else, is it possible for you to uninstall any cubeIDE on your pc and then reinstall the version 1.18.1 (prior to 1.19.0) and see if it helps?
If it doesn't, please create a thread on the tools forum board as this seems to be purely a cubeIDE issue...
Let me know what results your tests give.
Have a good day,
Julian
Hello, julian
Thank you so much for your help.
I confirm that I'm using the YAML file in the same folder as the model as recommended.
However, I still get the same "Range [0, -1) out of bounds" error.
I have also tested with STM32CubeIDE version 1.17.0, and I still encounter the same problem.
STM32N6/
│
├── 📁 Application/
│ │
│ ├── 📁 NUCLEO-N657X0-Q/ (For NUCLEO board)
│ │ ├── Inc/ (Header files)
│ │ │ ├── ai_model_config.h
│ │ │ ├── app_network.h
│ │ │ ├── FreeRTOSConfig.h
│ │ │ ├── main.h
│ │ │ ├── stm32n6xx_hal_conf.h
│ │ │ ├── stm32n6xx_it.h
│ │ │ └── ...
│ │ │
│ │ ├── Src/ (Source files)
│ │ │ ├── ai_model_config.c
│ │ │ ├── app_network.c
│ │ │ ├── main.c
│ │ │ ├── stm32n6xx_hal_msp.c
│ │ │ ├── stm32n6xx_it.c
│ │ │ └── ...
│ │ │
│ │ ├── STM32CubeIDE/
│ │ │ ├── .project
│ │ │ ├── .cproject
│ │ │ ├── STM32N657xx.ld
│ │ │ ├── Debug/
│ │ │ └── ...
│ │ │
│ │ └── Makefile
│ │
│ └── 📁 STM32N6570-DK/
│ ├── Inc/
│ │ ├── ai_model_config.h
│ │ ├── app_network.h
│ │ ├── FreeRTOSConfig.h
│ │ ├── main.h
│ │ ├── stm32n6xx_hal_conf.h
│ │ ├── stm32n6xx_it.h
│ │ └── ... (16 more headers)
│ │
│ ├── Src/ (Source files)
│ │ ├── ai_model_config.c (AI model init)
│ │ ├── app_network.c (Network execution)
│ │ ├── main.c (Main application)
│ │ ├── stm32n6xx_hal_msp.c (HAL MSP)
│ │ ├── stm32n6xx_it.c (Interrupts)
│ │ └── ... (7 source files total)
│ │
│ ├── STM32CubeIDE/
│ │ ├── .project
│ │ ├── .cproject
│ │ ├── STM32N657xx.ld
│ │ │
│ │ ├── Debug/
│ │ │ ├── Application/
│ │ │ ├── Drivers/
│ │ │ ├── Middlewares/
│ │ │ ├── ll_aton/
│ │ │ ├── lib_vision_models_pp/
│ │ │ ├── STM32N6570-DK_GettingStarted_ObjectDetection.elf
│ │ │ ├── STM32N6570-DK_GettingStarted_ObjectDetection.bin
│ │ │ └── makefile
│ │ │
│ │ ├── Application/
│ │ ├── Drivers/
│ │ ├── ll_aton/
│ │ ├── Middlewares/
│ │ ├── Utilities/
│ │ └── STM32N6570-DK_GettingStarted_ObjectDetection Debug.launch
│ │
│ └── Makefile
│
├── 📁 Binary/
│ ├── ai_fsbl.hex
│ ├── NUCLEO-N657X0-Q_GettingStarted_ObjectDetection.hex
│ ├── NUCLEO-N657X0-Q_network_data.hex
│ ├── STM32N6570-DK_GettingStarted_ObjectDetection.hex
│ └── STM32N6570-DK_network_data.hex
│
├── 📁 Doc/
│ ├── Application-Overview.md
│ ├── Boot-Overview.md
│ ├── Build-Options.md
│ ├── Deploy-your-tflite-Model-NUCLEO-N657X0-Q.md
│ ├── Deploy-your-tflite-Model-STM32N6570-DK.md
│ └── Program-Hex-Files-STM32CubeProgrammer.md
│
├── 📁 Middlewares/
│ │
│ ├── 📁 AI_Runtime/ (STM32 AI Runtime)
│ │ ├── Inc/ (93 headers)
│ │ ├── Lib/ (47 libraries)
│ │ ├── LICENSE.txt
│ │ └── Npu/
│ │
│ ├── 📁 ai-postprocessing-wrapper/ (Post-processing for AI)
│ │ ├── app_postprocess_od_st_yolox_ui.c (YOLO X post-processing)
│ │ ├── app_postprocess_od_yolov2_ui.c
│ │ ├── app_postprocess_od_yolov8_ui.c
│ │ ├── app_postprocess_od_st_ssd_uf.c (SSD post-processing)
│ │ ├── app_postprocess_od_fd_blazeface_ui.c (Face detection)
│ │ ├── app_postprocess.h
│ │ └── ... (25 files total)
│ │
│ ├── 📁 Camera_Middleware/
│ │ ├── cmw_camera.c
│ │ ├── cmw_camera.h
│ │ ├── ISP_Library/
│ │ ├── sensors/
│ │ │ ├── imx335/
│ │ │ ├── steval_55g1mbi/
│ │ │ └── steval_66gymai/
│ │ └── README.md
│ │
│ ├── 📁 lib_vision_models_pp/
│ │ └── lib_vision_models_pp/
│ │ ├── od_pp_st_yolox.c
│ │ ├── od_pp_yolov2.c
│ │ ├── od_pp_yolov8.c
│ │ ├── od_pp_ssd_st.c
│ │ └── ... (45 files)
│ │
│ └── 📁 screenl/
│ ├── display.c
│ ├── display.h
│ └── ... (38 files)
│
├── 📁 Model/
│ │
│ ├── st_yolo_x_nano_480_1.0_0.25_3_st_int8.tflite
│ ├── st_yolo_x_nano_480_1.0_0.25_3_config.yaml
│ │
│ ├── quantized_tiny_yolo_v2_224_.tflite
│ │
│ ├── 📁 my_mpools/ (Memory pool configs)
│ │ ├── stm32n6-app2_NUCLEO-N657X0-Q.mpool
│ │ └── stm32n6-app2_STM32N6570-DK.mpool
│ │
│ ├── 📁 NUCLEO-N657X0-Q/
│ │ ├── network_data.hex
│ │ ├── network.c
│ │ └── ...
│ │
│ ├── 📁 STM32N6570-DK/
│ │ ├── network.c
│ │ ├── network.h
│ │ ├── network_ecblobs.h
│ │ ├── network_generate_report.txt
│ │ ├── st_yolo_x_nano_480_1.0_0.25_3_st_int8_OE_3_2_0_Q.json
│ │ └── st_yolo_x_nano_480_1.0_0.25_3_st_int8_OE_3_2_0.onnx
│ │
│ ├── 📁 st_ai_output/
│ │ ├── network.c
│ │ ├── network.h
│ │ ├── network_ecblobs.h
│ │ └── ... (9 files)
│ │
│ ├── 📁 st_ai_ws/
│ │ ├── build_network/
│ │ ├── network.h
│ │ └── neural_art__network/
│ │
│ ├── generate-n6-model_NUCLEO-N657X0-Q.sh
│ ├── generate-n6-model_STM32N6570-DK.sh
│ ├── user_neuralart_NUCLEO-N657X0-Q.json
│ ├── user_neuralart_STM32N6570-DK.json
│ └── LICENSE.md
│
├── 📁 STM32Cube_FW_N6/
│ ├── Drivers/
│ │ ├── BSP/
│ │ ├── CMSIS/
│ │ └── STM32N6xx_HAL_Driver/ (1817 files)
│ │
│ ├── Middlewares/ (1593 files)
│ │ ├── FreeRTOS/
│ │ ├── USB_Device/
│ │ └── ...
│ │
│ ├── Utilities/ (24 files)
│ └── sbom_cdx.json
│
├── 📁 _htmresc/
│ ├── ASPECT_RATIO_MODE1.png
│ ├── BasicAppOverview.png
│ ├── Dev_mode.png
│ ├── Software_architecture.png
│ └── ... (20+ images)
│
├── stmaic_NUCLEO-N657X0-Q.conf (STM32 AI config for NUCLEO)
├── stmaic_STM32N6570-DK.conf (STM32 AI config for DK)
│Model/
│
├── 📁 my_mpools/
│ ├── stm32n6-app2_NUCLEO-N657X0-Q.mpool
│ └── stm32n6-app2_STM32N6570-DK.mpool
│
├── 📁 NUCLEO-N657X0-Q/
│ ├── network_data.hex
│ ├── network_data.xSPI2.bin
│ ├── network_ecblobs.h
│ └── network.c
│
├── 📁 STM32N6570-DK/
│ ├── LICENSE.txt
│ ├── network_atonbuf.xSPI2.raw
│ ├── network_c_info.json
│ ├── network_ecblobs.h
│ ├── network_generate_report.txt
│ ├── network.c
│ ├── network.h
│ ├── st_yolo_x_nano_480_1.0_0.25_3_st_int8_OE_3_2_0_Q.json
│ └── st_yolo_x_nano_480_1.0_0.25_3_st_int8_OE_3_2_0.onnx
│
├── 📁 st_ai_output/
│ ├── LICENSE.txt
│ ├── network_atonbuf.xSPI2.raw
│ ├── network_c_info.json
│ ├── network_ecblobs.h
│ ├── network_generate_report.txt
│ ├── network.c
│ ├── network.h
│ ├── st_yolo_x_nano_480_1.0_0.25_3_st_int8_OE_3_2_0_Q.json
│ └── st_yolo_x_nano_480_1.0_0.25_3_st_int8_OE_3_2_0.onnx
│
├── st_ai_ws/
│ ├── build_network/
│ ├── network.h
│ └── neural_art__network/
│
├── generate-n6-model_NUCLEO-N657X0-Q.sh (Generation scripts)
├── generate-n6-model_STM32N6570-DK.sh
│
├── LICENSE.md
│
├── quantized_tiny_yolo_v2_224_.tflite
│
├── st_yolo_x_nano_480_1.0_0.25_3_st_int8.tflite
│
├── st_yolo_x_nano_480_1.0_0.25_3_config.yaml
│
├── user_neuralart_NUCLEO-N657X0-Q.json
└─ user_neuralart_STM32N6570-DK.json
general:
project_name: st_yolo_x_480_deployment
model_path: ../../application_code/object_detection/STM32N6/Model/st_yolo_x_nano_480_1.0_0.25_3_st_int8.tflite
model_type: st_yolo_x
logs_dir: logs
saved_models_dir: saved_models
display_figures: false
global_seed: 127
operation_mode: deployment
dataset:
name: coco_2017_person
class_names: [person]
preprocessing:
rescaling:
scale: 1/127.5
offset: -1
resizing:
aspect_ratio: fit
interpolation: nearest
color_mode: rgb
postprocessing:
yolo_anchors: [0.5, 0.5, 0.07, 0.25, 0.23, 0.7]
confidence_thresh: 0.001
NMS_thresh: 0.5
IoU_eval_thresh: 0.5
max_detection_boxes: 100
tools:
stedgeai:
version: 10.2.0
optimization: balanced
on_cloud: False
path_to_stedgeai: C:/Users/@/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/10.2.0/Utilities/windows/stedgeai.exe
path_to_cubeIDE: C:/ST/STM32CubeIDE_1.19.0/STM32CubeIDE/stm32cubeide.exe
deployment:
c_project_path: ../../application_code/object_detection/STM32N6/
IDE: GCC
verbosity: 1
hardware_setup:
serie: STM32N6
board: STM32N6570-DK
mlflow:
uri: ./experiments_outputs/mlruns
hydra:
run:
dir: ./experiments_outputs/${general.project_name}
Hi,julian I tried with version 17. I managed to unlock the debug option, but after the second “Next”, I ran into an error.
have a good day,
Hi @Goat_abdalla,
I tried your object_detection_all_project and successfully ran it.
I had to delete the /debug, build the project and then delete the debug configuration.
I never encountered the range error.
Please try what I did, we never know, else, is it possible for you to uninstall any cubeIDE on your pc and then reinstall the version 1.18.1 (prior to 1.19.0) and see if it helps?
If it doesn't, please create a thread on the tools forum board as this seems to be purely a cubeIDE issue...
Let me know what results your tests give.
Have a good day,
Julian
