cvlab-yonsei / dkn

An official implementation of "Deformable Kernel Network for Joint Image Filtering" (IJCV 2020) in PyTorch.
GNU General Public License v3.0
75 stars 9 forks source link

about the bicubic result #6

Open redrock303 opened 3 years ago

redrock303 commented 3 years ago

I calculate the RMSE of bicubic, but I get 0.07168 (nyuv2 x8 setting) which is not consistent with your paper Table 3 (Bicubic Int. 14.22 ), I use the same dataset from your link(http://gofile.me/3G5St/2lFq5R3TL).

xuhuiling999 commented 1 year ago

I calculate the RMSE of bicubic, but I get 0.07168 (nyuv2 x8 setting) which is not consistent with your paper Table 3 (Bicubic Int. 14.22 ), I use the same dataset from your link(http://gofile.me/3G5St/2lFq5R3TL).

你好!你成功下载了他链接中的数据集了吗?如果你成功下载了,可否分享给我一下

redrock303 commented 1 year ago

I have uploaded this dataset at https://drive.google.com/drive/folders/13LhDom9xrAAePTvNL0tGvr5oymM_Bl6T?usp=sharing

I calculate the RMSE of bicubic, but I get 0.07168 (nyuv2 x8 setting) which is not consistent with your paper Table 3 (Bicubic Int. 14.22 ), I use the same dataset from your link(http://gofile.me/3G5St/2lFq5R3TL).

你好!你成功下载了他链接中的数据集了吗?如果你成功下载了,可否分享给我一下

Haonan-DONG commented 1 year ago

I have uploaded this dataset at https://drive.google.com/drive/folders/13LhDom9xrAAePTvNL0tGvr5oymM_Bl6T?usp=sharing

I calculate the RMSE of bicubic, but I get 0.07168 (nyuv2 x8 setting) which is not consistent with your paper Table 3 (Bicubic Int. 14.22 ), I use the same dataset from your link(http://gofile.me/3G5St/2lFq5R3TL).

你好!你成功下载了他链接中的数据集了吗?如果你成功下载了,可否分享给我一下

Sorry for deleting the data from the google link by mistake! Could you please upload the train_depth_split.npy to the google drive again?

Haonan-DONG commented 1 year ago

I calculate the RMSE of bicubic, but I get 0.07168 (nyuv2 x8 setting) which is not consistent with your paper Table 3 (Bicubic Int. 14.22 ), I use the same dataset from your link(http://gofile.me/3G5St/2lFq5R3TL).

你好!你成功下载了他链接中的数据集了吗?如果你成功下载了,可否分享给我一下

Sorry for deleting the data from the google link by mistake! Could you please also upload the train_depth_split.npy to the google drive again if you can see this commit? I can re-upload the data to the google drive. Thank you.

redrock303 commented 1 year ago

I have uploaded the missing file again at the same link.

lzz7 commented 1 year ago

I have uploaded the missing file again at the same link.

您好请问数据集中是否缺少一个"test_minmax.npy"的文件呢,我在运行代码后提示缺少test_minmax.npy这个文件,拜托了!

redrock303 commented 1 year ago

已上传

Haonan-DONG commented 1 year ago

I have uploaded the missing file again at the same link.

Thanks a lot.