chengshunli
chengshunli
 I canceled the LetterBox operation in the above location of the "ultralytics-main\ultralytics\data\dataset.py" file. This only affects the validation set. My operation process is: 1. Train model_1 with train_set_1 and...
@Y-T-G Why does this preprocessing affect the final detection accuracy? Isn't this processing only for the data of the validation set?
@Y-T-G Sorry, my test steps are like this. During testing, LetterBox processing is not used. It is only different during training. 1、Train model_1 with train_set_1 and val_set_1(with LetterBox). 2、Train model_2...
@Y-T-G Did you test the model with and without LetterBox operation?
@Y-T-G After my test, under the condition of ensuring the same training set and different test sets, the test results of the last.pt model are the same. But the LetterBox...
@Skillnoob How do we determine the size of an object? Is P3 responsible for detecting large objects, P4 for medium objects, and P5 for small objects?
Sorry, I don't quite understand what you mean? Could you explain it again? Thanks! @Skillnoob
! I found that I had confused the sizes of P3 and P5 before, thank you for correcting me! Regarding the question of target size, what I actually want to...
Thank you for your reply, the explanation is very clear, and thank you for your patience. I have another question, I wonder if you can give me some advice. In...
Thank you for your suggestion, I will read it carefully, thank you! @Y-T-G