Question/Issue:
Hello, I’m new to this kind of topic but I want to to put a tflite model on a RaspberryPi4 to make a bin that sorts by itself. I already put together 3k+ images for my dataset (which is not optimised yet I guess). I simply followed the steps but when it comes to training with FOMO I have 0% precision because not a single object is detected.
Do you have some clues about what is happening? Thank you in advance
Hi
I can see that many of the images are taken at different distances, try to keep the distance and background, and lighting consistent for initial training. Did you follow our tutorial or webinar on FOMO?
There are also a number of other projects using other sensors you can refer to:
Best
Eoin