dimensionality-driven-learning
dimensionality-driven-learning copied to clipboard
xingjunm
LID increase with acc
Thank you for sharing the codes and your paper is very inspiring. But I test 'python train_newmodels.py -d cifar-10 -m d2l -e 50 -b 128 -r 0
',and find the results is not like that in your paper: the LID increase while the Test acc increase ,which is different from the statement in your paper
cifar-10/ 50 epochs /20%noise:
cifar-10/ 50 epochs /0%noise:
cifar-10/150epochs/0%noise:
the results in your paper:
