Submission failed : Failed to communicate with the grader

This issue has been resolved now. Please do let us know if you continue to face this issue.

Best,
Mohanty

View post 0

Feedback and suggestion

@andrey1362010 : A person who is a citizen of Russia and is currently a resident of another eligible country, with an active bank account present in that eligible country, is eligible to receive prizes.

View post 1

Feedback and suggestion

Apologies for the relative radio silence due to the holiday season.

GPUs

We are still waiting for a response from the organizing team about the provision of GPUs, so we will have to hold off on answering the question until we hear back from the organizing team.

Throughputs

We are investigating the issue with differential throughputs across different evaluations. A new instance is instantiated for every evaluation on our cloud provider, and the instance type is exactly the same - and hence the resources available. We have confirmed that the exact same instance type is being made available to all the submissions as well. We will get back to you with more details on this soon as well.

Timeouts

The current timeouts are 1hr, or 60 mins.

Apologies on the slow response times due to the Holiday season. We will be providing support at full capacity again starting 2nd of January, 2023.

Best,
Mohanty

View post 1

Evaluation failed due to system error

@yoyololicon : It seems that the evaluators are unable to open some of the generated files. Can you please test locally if you can read the generated predictions using PySoundFile.

Best,
Mohanty

View post 0

Feedback and suggestion

@lyghter : The team leader will be the main legal POC with AIcrowd, and the prizes will be transferred to the team leader. Any prize-sharing agreements between the team leader and the rest of the team members are internal to the team.

View post 1

Feedback and suggestion

We are discussing this with the organizing committee, and will get back to you soon on this.

View post 0

Feedback and suggestion

@lyghter : Unfortunately, residents of Russia are not eligible for the prizes in the Challenge. And in case, a leaderboard position is held by a team which is not eligible for the prizes, then the prizes will indeed be rolled over to the next position (and at this point, it will not be possible for us to logistically allow non eligible teams to pass on the prizes to a charity). The rules have been updated to categorically reflect that.

View post 2

Feedback and suggestion

We are constantly trying to make this challenge better for you and would appreciate any feedback you might have .

Please reply to this thread with your suggestions and feedback on making the challenge better for you!

• What have been your major pain points so far?
• What would you like to see improved?

Cheers,
SDX Challenge Team

View post 0

Looking for teammates?

Competing is more fun with a team!

Introduce yourself here, and find others who are looking to team up!

Format

• A short introduction about you and your background.
• What brings you to this challenge?
• Some ideas you wish to explore as a part of this challenge ?

Cheers,

SDX Challenge Team

View post 0

About my submissions

@victorkras2008 : can you please try again. You should be able to access the submission lists on both the challenges.

View post 0

About my submissions

@victorkras2008 : You should be able to see all your submissions in the submissions tab, for ex: AIcrowd | Semantic Segmentation | Submissions

View post 0

💬 Feedback and suggestion

@ricardodeazambuja : Yes the observation is correct.

As described here:

The dataset contains 422 flights, 2056 total frames (5 frames per flight at different AGLs),  Full semantic segmentation annotations of all frames and depth estimations. The dataset has been split into training and (public) test datasets. While the challenge will be scored using a private test dataset, we considered it useful to have this split to allow teams to share their results even after the challenge ends.

Of the total frames available, a subset if used for the (public) test set that you are currently being scored on. There will be an additional (private) test set that the final leaderboards will be based on. And submissions are currently limited to 5 submissions / day.

Best,
Mohanty

View post 0

👥 Looking for teammates?

View post 0

💬 Feedback and suggestion

View post 0

Welcome to Scene Understanding for Autonomous Drone Challenge

View post 0

About leaderboard sorting

@victorkras2008 : yes the sorting on the leaderboard is correct. In case of Scale invariant logarithmic error (SILog), a lower score is better.

View post 0

Bad link to "Baseline for Mono Depth Perception" 📅

@victorkras2008 : Thanks for pointing it out.The links are correct, we realized that theres a few more things that need to be updated in the repo before they can be made public. So sorry for the confusion, we will try to make the repositories public as soon as we can.

Thanks,
Mohanty

View post 0

Evaluation failed: Findcave Inference: Error (exit code 1): ValueError: Not allowed to access task

@slai7880 : the Findcave reference in the logs for the intro track is a bug only specific to the logs, and because of how we are re-using the evaluators from the other track.
In case of the intro track, the Findcave rollout is hot-patched to use the ObtainDiamond env instead. So the logs show Findcave even if it is actually using ObtainDiamond. Sorry for the confusion.

Regarding the error at your end, this is because, of this line: AIcrowd

where during the evaluation phase, the participant submitted agents are not allowed to access the internal env specific parameters like env.task. This is to prevent agents from interfering with the internal state of the env during the evaluation.

Best,
Mohanty

View post 0

Debug Submission with debug=false

@k_sashank : The link above doesnt point to the issue page.
However we noticed that debug is set to False in your master branch. But the code used in your last submission (AIcrowd) still uses debug as True.

Please make a new submission from the master branch of your code repository.

View post 0

Getting run failures without any logs

@felipe_b : The issue with the logs not showing for some submissions has been fixed. The logs from the latest failure is available here : AIcrowd

It seems that the software runtime specification is not done correctly, and the image build phase fails because some of the dependencies are not specified correctly.

View post 1