Open JoonHyeokJ opened 2 years ago
Hi,
Thanks for your amazing work.
I also had the same problem when reproducing your result and I was a little bit confused.
I saw that recently in your README, you stated that ADL was trained on the grey Flickr2K dataset only. Is this model only be used for de-noising BSD dataset?
And in the paper, the model that trained on ImageNet is only used for Medical image de-noising, not for BSD dataset denoising?
Thanks in advance.
Hello! I have a question about training time. How long does the training take?
I'm reproducing ADL. I am training ADL with ImageNet, following the training details in ADL paper. But according to my calculations, this training may take a few hundred days with default batch size=4, even though I modified the period of test from 200 to 4000000.
I think this training time doesn't make sense because it's too long. Even if I modify the batch size from 4 to 32 or more, this training is expected to take at least several tens of days.
So, I wonder how long did your traing take on ImageNet? And what did you set the batch size to? Or is there any other detailed setting for training?
Thank you for your reading!