Open mlkk518 opened 9 months ago
Sorry for the late reply. What's the result of your training?
Thanks for your reply. I finally found that you finetuned your mode with the Div2K. I am sorry to tell you the detailed results. I remember that it is just lower than your results. Thanks a lot. Recently, I am too busy to reply you late. I guess if I finetune with the Div2k, and a comparebal results may be derived.
Best Regard!
Junhui Li.
From | Chong ***@***.***> |
Date | 12/01/2023 08:55 |
To | ***@***.***> |
Cc | ***@***.***>、***@***.***> |
Subject | Re: [MC-E/Deep-Generalized-Unfolding-Networks-for-Image-Restoration] The training set for training compressive sensing task (Issue #9) |
Sorry for the late reply. What's the result of your training?
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.
Hi, thanks for your efforts. I reproduced your work with the BSD400 dataset for the compressive sensing task. However, I trained for several days, but the results are far from your reported results. Is there any trick for the training? Thanks very much! (The model parameters are large, while the training images are few. )