I checked locally with all my files and none of them went over the time limit or above 300 seconds for any images.
Please let me know what is going wrong and how i can fix it? Thanks
Created by Har Shwinder Singh hssingh Oh, I see. Maybe my model causes too much time to run. Thank you for your help @hssingh. Your problem might actually be the time constraint itself , my code threw me an error that only the CPU was being used, are you getting the same error as well? If not , it is a different issue of time constraint I tried FROM nvidia/cuda:11.4.1-base-ubuntu20.04 too but it doesn't fix the problem.
I still got No *.nii.gz files found; please check whether running the Docker container locally will result in a NIfTI file within the time constraint.
I just followed the solution vchung posted,
Changing the FROM ubuntu to FROM nvidia/cuda:11.4.1-base-ubuntu20.04 in the dockerfile.
Does that not work for you or does that cause new errors? Maybe describe what happens once you use FROM nvidia/cuda:11.4.1-base-ubuntu20.04 and I can try see whats wrong Hello @hssingh,
I have the same problem.
I've tried several ways but all of those work.
Can you guide me how to fix this problem, please?
Thank you very much. Hi @hssingh,
Thank you for your interest.
Currently, we are not accepting any new submissions for evaluation on the validation dataset. We will share the detailed information regarding 'validation evaluation' at the conclusion of the challenge. Ah i was trying to find this information but i couldnt. Thank you for the update, so that means I am now done and will wait for your update. Additionally, do ya'll plan to turn the valdiation submissions after everything is wrapped up? Please let us know , thanks!
@hssingh ,
Apologies for the confusion. An update was sent out last month with respect to this phase, specifically:
> When you submit your docker image, we will run them against 5 cases from the validation data to make sure your containers run, then we will run them against the unseen test set.
Information pertaining to the test data is to not be shared with the participants, which is why we are using the validation data to help with debugging at this time.
Hope this helps clarify things! Oh it finally actually worked, but it only tested on 5 cases? Does that mean i need to submit once again to finalize? Please let me know, thanks! I've tried those methods and still it doesnt seem to work. Anything else that I can try? If it works in my local env why wouldnt it work outside since it is a container? Hi @hssingh ,
Looking at the [log file](https://www.synapse.org/#!Synapse:syn26232419) of submission 9716197, it seems a RuntimeWarning was encountered. I am not sure why this exception was thrown, as we do specify a GPU (with `runtime=nvidia`) when running Docker containers:
```
docker run --rm \
--network none \
--runtime="nvidia" \
-v /path/to/input:/input:ro \
-v /path/to/output:/output:rw \
{docker image}
```
A fellow participant has suggested a fix [here](https://www.synapse.org/#!Synapse:syn25829067/discussion/threadId=8379&replyId=25879); perhaps this can help? I did a local test on my T4 Gpus and it took around 42 seconds for one file.
Please help me out asap so i can submit before the deadline, ive worked very hard to get the docker running and working.
Appreicate your help!
Drop files to upload
Check Your submission (id: 9716197) is invalid : No *.nii.gz files found; locally will result in a NIfTI file within the time constaint page is loading…