2025-05-09 1:26 PM - edited 2025-05-09 1:50 PM
Hi all,
I'm running into an issue when trying to deploy a model from to my STM32N6 board.
I am following this guide: https://github.com/STMicroelectronics/stm32ai-modelzoo-services/blob/main/object_detection/deployment/README_STM32N6.md
running script:
python stm32ai_main.py --config-path ./config_file_examples/ --config-name deployment_n6_yolov8_config.yaml
But ending up with following error:
deployment yaml:
general:
model_path: https://github.com/stm32-hotspot/ultralytics/raw/refs/heads/main/examples/YOLOv8-STEdgeAI/stedgeai_models/object_detection/yolov8n_256_quant_pc_uf_od_coco-person-st.tflite
model_type: yolo_v8
operation_mode: deployment
dataset:
class_names: [person]
preprocessing:
resizing:
aspect_ratio: crop
interpolation: nearest
color_mode: rgb
postprocessing:
confidence_thresh: 0.6
NMS_thresh: 0.5
IoU_eval_thresh: 0.4
max_detection_boxes: 10
tools:
stedgeai:
version: 10.0.0
optimization: balanced
on_cloud: False
path_to_stedgeai: C:/ST/STEdgeAI/2.1/Utilities/windows/stedgeai.exe
path_to_cubeIDE: C:/ST/STM32CubeIDE_1.18.0/STM32CubeIDE/stm32cubeide.exe
deployment:
c_project_path: ../../application_code/object_detection/STM32N6/
IDE: GCC
verbosity: 1
hardware_setup:
serie: STM32N6
board: STM32N6570-DK #STM32H747I-DISCO, STM32N6570-DK
mlflow:
uri: ./experiments_outputs/mlruns
hydra:
run:
dir: ./experiments_outputs/${now:%Y_%m_%d_%H_%M_%S}
Any ideas what I am doing wrong ?
OS: Windows 11
Solved! Go to Solution.
2025-05-13 2:24 PM
Hi Team,
I wanted to share that I’ve successfully resolved the issue we were encountering. The problem stemmed from a line in compile.py which I needed to modify.
The original command failed to execute correctly when the --output and --workspace paths were the same:
C:\ST\STEdgeAI\2.1\Utilities\windows\stedgeai.exe generate --target stm32n6 -m ../../../stm32ai-modelzoo/object_detection/ssd_mobilenet_v2_fpnlite/ST_pretrainedmodel_public_dataset/coco_2017_person/ssd_mobilenet_v2_fpnlite_035_192/ssd_mobilenet_v2_fpnlite_035_192_int8.tflite --output C:\STM-Coding\stm32ai-modelzoo-services\object_detection\src\experiments_outputs\2025_05_13_21_59_34 --workspace C:\STM-Coding\stm32ai-modelzoo-services\object_detection\src\experiments_outputs\2025_05_13_21_59_34 --st-neural-art default@../../application_code/object_detection/STM32N6/Model/user_neuralart.json --input-data-type uint8 --inputs-ch-position chlast
2025-05-13 2:24 PM
Hi Team,
I wanted to share that I’ve successfully resolved the issue we were encountering. The problem stemmed from a line in compile.py which I needed to modify.
The original command failed to execute correctly when the --output and --workspace paths were the same:
C:\ST\STEdgeAI\2.1\Utilities\windows\stedgeai.exe generate --target stm32n6 -m ../../../stm32ai-modelzoo/object_detection/ssd_mobilenet_v2_fpnlite/ST_pretrainedmodel_public_dataset/coco_2017_person/ssd_mobilenet_v2_fpnlite_035_192/ssd_mobilenet_v2_fpnlite_035_192_int8.tflite --output C:\STM-Coding\stm32ai-modelzoo-services\object_detection\src\experiments_outputs\2025_05_13_21_59_34 --workspace C:\STM-Coding\stm32ai-modelzoo-services\object_detection\src\experiments_outputs\2025_05_13_21_59_34 --st-neural-art default@../../application_code/object_detection/STM32N6/Model/user_neuralart.json --input-data-type uint8 --inputs-ch-position chlast