Performance

Open jiandandan001 opened this issue 4 years ago • 1 comments

Hi, Thank you for sharing the code.

I retrained the IMDN and IMDN_BALANCED_ATTENTION without using pretrained models. However, the PSNR and SSIM are lower than the results shown in the paper.

Is there any tricks? Thanks.

Dec 03 '21 08:12 jiandandan001

你可以试着finetune一下，我这边训练设备是1080TI（8G）*2，batchsize（越大越好）可能会有出入，iteration上也会有出入，patchsize（越大越好）也开不了很大，提供的权重，是用训练集实实在在跑出来的

------------------ 原始邮件 ------------------ 发件人: "dandingbudanding/BAM" @.>; 发送时间: 2021年12月3日(星期五) 下午4:09 @.>; @.***>; 主题: [dandingbudanding/BAM] Performance (Issue #6)

Hi, Thank you for sharing the code.

I retrained the IMDN and IMDN_BALANCED_ATTENTION without using pretrained models. However, the PSNR and SSIM are lower than the results shown in the paper.

Is there any tricks? Thanks.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.

Dec 13 '21 02:12 dandingbudanding