Instructions

[daddydrac]

Can you please create better detailed instructions in the README on how to perform inference and training? I am running into many errors. If you do this, I would contribute a Docker container for better reproducibility for this.

[xuebinqin]

sorry about that. please open an issue to show us the exact errors.

On Fri, Aug 12, 2022 at 1:37 PM salinaaaaaa @.***> wrote:

Can you please create better detailed instructions in the README on how to perform inference and training? I am running into many errors. If you do this, I would contribute a Docker container for better reproducibility for this.

— Reply to this email directly, view it on GitHub https://github.com/xuebinqin/DIS/issues/27, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORIYTFA6OCQ2CNCJCMTVY2YXRANCNFSM56MZYXKQ . You are receiving this because you are subscribed to this thread.Message ID: @.***>

-- Xuebin Qin PhD Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage: https://xuebinqin.github.io/

[hobo1618]

Hey I'm a total noob, also getting errors when I follow step 4:

/home/hobo/.local/lib/python3.8/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='mean' instead. warnings.warn(warning.format(ret)) building model... batch size: 8 --- create training dataloader --- ------------------------------ train -------------------------------- --->>> train dataset 0 / 1 DIS5K-TR <<<--- -im- DIS5K-TR ../DIS5K/DIS-TR/im : 3000 -gt- DIS5K-TR ../DIS5K/DIS-TR/gt : 3000 1 train dataloaders created --- create valid dataloader --- ------------------------------ valid -------------------------------- --->>> valid dataset 0 / 1 DIS5K-VD <<<--- -im- DIS5K-VD ../DIS5K/DIS-VD/im : 470 -gt- DIS5K-VD ../DIS5K/DIS-VD/gt : 470 1 valid dataloaders created --- build model --- --- define optimizer --- /home/hobo/.local/lib/python3.8/site-packages/torch/nn/functional.py:3509: UserWarning: nn.functional.upsample is deprecated. Use nn.functional.interpolate instead. warnings.warn("nn.functional.upsample is deprecated. Use nn.functional.interpolate instead.") /home/hobo/.local/lib/python3.8/site-packages/torch/nn/functional.py:3631: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. warnings.warn( [1] 7685 killed /bin/python3 /home/hobo/Documents/dev/DIS/IS-Net/train_valid_inference_main.p

Any idea what's wrong please? Thanks so much

[xuebinqin]

The warning should be fine, it won't hurt the performance. That's because newer version pytorch change the F.upsample to F.interpolate, you can search for the upsample function and replace it with the "interpolate" function. Or you can downgrade your pytorch version.

On Fri, Sep 2, 2022 at 12:00 PM Will @.***> wrote:

Hey I'm a total noob, also getting errors when I follow step 4:

/home/hobo/.local/lib/python3.8/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='mean' instead. warnings.warn(warning.format(ret)) building model... batch size: 8 --- create training dataloader --- ------------------------------ train -------------------------------- --->>> train dataset 0 / 1 DIS5K-TR <<<--- -im- DIS5K-TR ../DIS5K/DIS-TR/im : 3000 -gt- DIS5K-TR ../DIS5K/DIS-TR/gt : 3000 1 train dataloaders created --- create valid dataloader --- ------------------------------ valid -------------------------------- --->>> valid dataset 0 / 1 DIS5K-VD <<<--- -im- DIS5K-VD ../DIS5K/DIS-VD/im : 470 -gt- DIS5K-VD ../DIS5K/DIS-VD/gt : 470 1 valid dataloaders created --- build model --- --- define optimizer --- /home/hobo/.local/lib/python3.8/site-packages/torch/nn/functional.py:3509: UserWarning: nn.functional.upsample is deprecated. Use nn.functional.interpolate instead. warnings.warn("nn.functional.upsample is deprecated. Use nn.functional.interpolate instead.") /home/hobo/.local/lib/python3.8/site-packages/torch/nn/functional.py:3631: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. warnings.warn( [1] 7685 killed /bin/python3 /home/hobo/Documents/dev/DIS/IS-Net/train_valid_inference_main.p

Any idea what's wrong please? Thanks so much

— Reply to this email directly, view it on GitHub https://github.com/xuebinqin/DIS/issues/27#issuecomment-1235814892, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORMNSJVKBS4BZINNIBDV4JFDHANCNFSM56MZYXKQ . You are receiving this because you commented.Message ID: @.***>

-- Xuebin Qin PhD Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage: https://xuebinqin.github.io/