Hi, I would like to know about how the annotation works. I like to know that the results are same or not when training.
10 annotation in 1 image vs 10 images with 1 annotation in 1 image, which is better? Which one got the better results?
Hi - generally, you want your training data to be the same as your production data.
Smaller images get the benefit of training and inferencing faster, though you may need to tile the images or use a method like SAHI.
This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.