Closed zhaoedf closed 2 years ago
Hello, I've saw your issue. I'll first look into https://github.com/arthurdouillard/dytox/issues/5, which may (or not) explain your issue and #2
I'll get back to you asap. Sorry for the inconvenience.
Hello, I've saw your issue. I'll first look into #5, which may (or not) explain your issue and #2
I'll get back to you asap. Sorry for the inconvenience.
ok, i totally understand.
Hi @arthurdouillard
I also tried ImageNet-100 and got a similar result as @zhaoedf.
BTW, I wonder that is it possible to share your trained checkpoints with us?
Hi all, I also tried ImageNet-1000 but got a lower result:( I am using Pytorch 1.10.1, CUDA 10.1
I'll try to use a different Pytorch version and try again.
Please see erratum.
for cifar and imagenet-1000, i can get similar results as what paper reported. how ever, for imangenet-100 only, i cannot get the same result, with 3~4% deviation.
the followings are my running scripts and experiment results.
scipts
results (i ran two times on different machines)
i focus on both avg and last acc.