Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Esp32-cam with teachable machine #25

Open
boylucky opened this issue Apr 20, 2024 · 0 comments
Open

Esp32-cam with teachable machine #25

boylucky opened this issue Apr 20, 2024 · 0 comments

Comments

@boylucky
Copy link

boylucky commented Apr 20, 2024

Hello fustyles. Please would it be possible to get in discussion with you about ESP32-CAM in connection with teachable machine? I see you have a lot of great project about it. I have some experiences with Raspberry Pi and teachable machine and now I build project with ESP32-CAM but getting some troubles with comp vision there. In the beginnig I wanted to use teachable machine tflite model on ESP32-CAM but I was not able to shrink it to fit ESP hardware. So later I decided to switch to micropython and used a bit different approach for my purpose without the tflite. But it is not always as accurate as I would need. Do you think it would be somehow possible to implement tflite from Google teachable machine with micropython on ESP32-CAM? Do you have any experience with it? Or do you think it would be possible to stay with Arduino IDE code for comp vision compiled to binary and used in micropython then? I think it would be to complicated and slow if even possible. I guess it would be propably better to rewrite the micropython code to Arduino style code. If So please would you recomand which of your project would suite best to following needs?

  1. I need to take picture with ESP32-CAM
  2. Extract only some parts (squares) of the taken photo (parts will be specified by x and y coordinates of corners) and each clasify with tflite model from Google teachable machine. Any advice will be appreciated.

Thanks and have a good Day.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant