search

jiangsutx / SRN-Deblur

Repository for Scale-recurrent Network for Deep Image Deblurring
http://www.xtao.website/projects/srndeblur/srndeblur_cvpr18.pdf
MIT License
719 stars 185 forks source link

How do you compute the param of SRN-Deblur model?3.76M? #48

Open Courageux-J opened 4 years ago

Courageux-J commented 4 years ago

image

tejpratapgit commented 4 years ago

Hello courageux, How many params did you get. We observed ~6.8M params by excluding adam optimzer training params.

jiangsutx commented 4 years ago

There is a difference between released model and this table. We mentioned in the paper that in this table conv kernels are 3x3, in order for fast experiments. And in release model, kernels are 5x5.

tejpratapgit commented 4 years ago

Ok. Thank you.

Regards, Tej

On Mon, 16 Dec 2019, 9:11 am Xin Tao, notifications@github.com wrote:

There is a difference between released model and this table. We mentioned in the paper that in this table conv kernels are 3x3, in order for fast experiments. And in release model, kernels are 5x5.

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/jiangsutx/SRN-Deblur/issues/48?email_source=notifications&email_token=AFM3USTH2KK4HWNSY6O32NDQY32F5A5CNFSM4JZKLPU2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEG5NNQQ#issuecomment-565892802, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFM3USXE2HXEZ5UJVS3UBGLQY32F5ANCNFSM4JZKLPUQ .

noranali commented 1 year ago

hello , could you help me to compute the model parameters please ?