Closed duanzhiihao closed 4 years ago
It seems that there are duplicated images in datasets/ILSVRC2015/ImageSets/DET_train_30classes.txt, which can be confirmed by the following script.
datasets/ILSVRC2015/ImageSets/DET_train_30classes.txt
lines = open('DET_train_30classes.txt', 'r').read().strip().split('\n') print(len(lines)) # 53639 print(len(set(lines))) # 53237
Is there a reason that you use duplicated training images?
This file is directly copied from the FGFA repo and I did not check whether duplicated training images exist. This would not influence the final performance in my opinion.
Thanks, I agree.
It seems that there are duplicated images in
datasets/ILSVRC2015/ImageSets/DET_train_30classes.txt
, which can be confirmed by the following script.Is there a reason that you use duplicated training images?