Replies: 2 comments 3 replies
-
Use the menu |
Beta Was this translation helpful? Give feedback.
3 replies
-
The model is a trained neural network. It cannot be trained on the ESP32. Even on modern computers it takes quite some time (30-90 Minutens). The way to go is: collect wrong detected images, label them and support them as training data. You can do also your own training: https://github.com/jomjol/AI-on-the-edge-device/wiki/Learn-models-with-your-own-images |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
The Feature
Is there somewhere to tell the system that the detected value is wrong and enter a correction?
a workout?
If yes, where?
I use version 13.0.7 with a gas meter.
Thanks Micha
Beta Was this translation helpful? Give feedback.
All reactions