Object Detection application to enable the deployment of object detection models on STM32N6570-DK and NUCLEO-N657X0-Q boards.
This application is prebuilt with an object detection model.
- Sequential application flow
- NPU accelerated quantized AI model inference
- Dual DCMIPP pipes
- DCMIPP crop, decimation, downscale
- DCMIPP ISP usage
- LTDC dual-layer implementation
- Dev mode
- Boot from External Flash
| Name | Version | Release notes |
|---|---|---|
| STM32Cube.AI runtime | v12.0.0 | |
| ai-postprocessing-wrapper | v1.1.0 | release notes |
| screenl | v3.0.2 | release notes |
| Camera Middleware | v1.5.1 | release notes |
| stm32-vision-models-postprocessing Library | v0.14.2 | release notes |
| CMSIS | v6.2.0 | release notes |
| STM32N6xx CMSIS Device | v1.3.0 | release notes |
| STM32N6xx HAL/LL Drivers | v1.3.0 | release notes |
| STM32N6570-DK BSP Drivers | v1.3.0 | release notes |
| NUCLEO-N657X0-Q BSP Drivers | v1.2.0 | release notes |
| BSP Component aps256xx | v1.0.6 | release notes |
| BSP Component Common | v7.3.0 | release notes |
| BSP Component mx66uw1g45g | v1.1.0 | release notes |
| BSP Component rk050hr18 | v1.0.1 | release notes |
| Fonts Utility | v2.0.3 | release notes |
| lcd Utility | v2.2.0 | release notes |
| ai fsbl | v1.4.0 | release notes |
- README.md
- Doc/Application-Overview.md
- Doc/Boot-Overview.md
- Doc/Build-Options.md
- Doc/Neural-ART-Description-and-Operation.md
- Doc/Deploy-your-Quantized-Model.md
- Doc/Program-Hex-Files-STM32CubeProgrammer.md
- New configuration for ModelZoo allows deploying larger models by storing epoch controller blob in flash memory
- Update inference function
- Update STEdgeAI to v4.0.0
- Update ai-postprocessing-wrapper to v1.1.0
- Add Yolo-D and new SSD models support
- Update lib_vision_models_pp to v0.14.2
- Update ai-postprocessing-wrapper to v1.0.10
- Update Camera Middleware to v1.5.0, adding VD1943 support
- Update lib_vision_models_pp to v0.13.0
- Update ai-postprocessing-wrapper to v1.0.9
- Update Cube FW to v1.3.0
- Update STEdgeAI to v3.0.0
- Switch to STEdgeAI
st-aiAPI
- Update Camera Middleware to v1.4.3
- Update lib_vision_models_pp to v0.10.0
- Update ai-postprocessing-wrapper to v1.0.7
- Update screenl to v3.0.0
- Documentation improvements
- Update to Cube FW to v1.2.0
- Update to STEdgeAI v2.2.0
- Add int8 post processing support for:
- Object detection Yolo v2
- Object detection Yolo v8
- Object detection ST Yolo X
- Single pose estimation Movenet
- Multi pose estimation Yolo v8
- Semantic segmentation Deeplab v3
- Add support for BlazeFace post processing
- Add support of the NUCLEO-N657X0-Q board
- Update miscellaneous drivers
- Update Camera Middleware to v1.4.2
- Miscellaneous refactoring
Initial Release