openmv/src/stm32cubeai
luzpaz 971f14daab misc: Fix typos in src/omw subdirectory
Found via `codespell -q 3 -S "*.pgm,*.ppm,./src/hal,./src/drivers" -L als,dout,erro,extint,hsi,inout,ois,paeth,re-use,ser,serie`
2023-09-16 17:01:42 +00:00
..
AI Merge pull request #620 from thibthibaut/license 2019-10-24 17:17:04 +02:00
example Integration of STM32Cube.AI in the firmware 2019-10-15 16:17:17 +02:00
imgs Updated README.md: deleted detailed steps, added link to ST wiki for step-by-step tutorial (#1310) 2021-05-13 06:58:39 +02:00
cube.mk Use USER_C_MODULES to add OpenMV modules. 2021-08-11 21:48:16 +02:00
LICENSE Integration of STM32Cube.AI in the firmware 2019-10-15 16:17:17 +02:00
Makefile Fix stm32cubeai Makefile. 2020-12-16 21:39:51 +02:00
nn_st.c misc: Fix typos in src/omw subdirectory 2023-09-16 17:01:42 +00:00
nn_st.h Integration of STM32Cube.AI in the firmware 2019-10-15 16:17:17 +02:00
py_st_nn.c micropython: Update all types to use the new type definition. 2023-05-07 13:18:35 +02:00
README.md Updated README.md: deleted detailed steps, added link to ST wiki for step-by-step tutorial 2021-05-07 20:41:51 -07:00

STM32Cube.AI enabled OpenMV firmware

This package provides the source code for compiling the OpenMV H7/H7+ firmware with STM32Cube.AI enabled.

It is a modified version of the official OpenMV firmware enabling STM32Cube.AI optimized neural networks.

The process for using STM32Cube.AI with OpenMV is described in the following figure.

Process to use Cube.AI with OpenMV

Starting from a trained network model, such as a .h5 Keras model or .tflite TensorFlow Lite model, STM32Cube.AI will generate the optimized C code of the neural network. The generated files need to be copied into this project, then the firmware should be compiled using the GNU ARM Toolchain. Finally, the binary has to be flashed onto the OpenMV target using OpenMV IDE or STM32CubeProgrammer and the user will be able to program the board using microPython and call the neural network prediction function.

How to add AI model generated by STM32Cube.AI to OpenMV ecosystem

For detailed steps, please follow this step-by-step tutorial on STM32 wiki: How to add AI model to OpenMV ecosystem

License informations

  • The python wrapper i.e the sources files nn_st.c, nn_st.h, py_st_nn.c are under MIT License. See LICENSE file for more information.
  • All files (header file and compiled library) present in the AI directory are under the SLA0044 licence. See AI/LICENCE for more information.