TypeError: forward() missing 1 required positional argument: 'data'

[mhliao]

TypeError: forward() missing 1 required positional argument: 'data'

[MhLiao]

@deepseek I think @ws-lin is right. Could you please try to use CUDA_VISIBLE_DEVICES=0 in the command.

[ws-lin]

I set it to work on just one gpu

@liangkaihuan Thanks for the hint,
I found the solution, the issue was caused because I had CUDA Version 10.0.130, while @MhLiao tutorial had cudatoolkit=10.1.
In my case, the solution was to use cudatoolkit=10.0
Thanks all

[ws-lin]

the same error

[llkn-2]

I changed model.py(line:56) to
if self.training:
pred = self.model(data, training=self.training)
else:
pred = self.model(data)
and solved the problem.

@ws-lin What code values did you change to solve this?
@liangkaihuan Upload your modified model.py here so i can test.

@MhLiao CUDA_VISIBLE_DEVICES=0 allows to continue the process, but the end is "Segmentation fault", and in results folder nothing is recognized.

(db) home@home-desktop:~/p9/DB$ CUDA_VISIBLE_DEVICES=0 python eval.py experiments/seg_detector/totaltext_resnet18_deform_thre.yaml --resume ./modelz/totaltext_resnet18 --polygon --box_thresh 0.6
./datasets/total_text/
[INFO] [2019-12-05 20:11:06,534] Resuming from ./modelz/totaltext_resnet18
[INFO] [2019-12-05 20:11:06,563] Resumed from ./modelz/totaltext_resnet18
100%|██████████████████████████████████████████████████████████████████████████████████████| 300/300 [00:10<00:00, 27.78it/s]
[INFO] [2019-12-05 20:11:17,641] precision : 0.000000 (300)
[INFO] [2019-12-05 20:11:17,641] recall : 0.000000 (300)
[INFO] [2019-12-05 20:11:17,641] fmeasure : 0.000000 (1)
Segmentation fault

[llkn-2]

I tested CUDA_VISIBLE_DEVICES=0 without modifying code, and the forward() missing error can also be solved. I think Segmentation fault in your case may come from incorrect compilation of deformable convolution.

[leedewdew]

use CUDA_VISIBLE_DEVICES=0 can't always solve this problem when run the demo.
It still tells "TypeError: forward() missing 1 required positional argument: 'data'" .
Are there some other problems?

[leedewdew]

use CUDA_VISIBLE_DEVICES=0 can't always solve this problem when run the demo.
It still tells "TypeError: forward() missing 1 required positional argument: 'data'" .
Are there some other problems?

After hundreds of time trying, I find the issue is "CUDA_VISIBLE_DEVICES=0" doesn't take effect in my centos, while add one line of "os.environ["CUDA_VISIBLE_DEVICES"] = '3'" in demo.py finally saved me.

[ygean]

The problem is here: DataParallel doesn't properly handle kwargs

[qiaoyaya2011]

@deepseek it doesn't work. cuda version is equal cudatoolkit version.