Loading
0 Follower
0 Following
rauf_kurbanov

Location

US

Badges

1
0
0

Activity

Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Mon
Wed
Fri

Ratings Progression

Loading...

Challenge Categories

Loading...

Challenges Entered

Latest submissions

See All
graded 20974
graded 20973
graded 17021
Participant Rating
Participant Rating
rauf_kurbanov has not joined any teams yet...

NeurIPS 2019 : Disentanglement Challenge

Mismatch of Report Submission time; openreview closed before scheduled!

Over 4 years ago

Well I hope they will fix it, since the AoE time was used in the original deadline.

Mismatch of Report Submission time; openreview closed before scheduled!

Over 4 years ago

I also can’t submit. Which is very troubling 30 minutes prior to deadline

Why my solution was not evaluated yet?

Over 4 years ago

Guys, all the submission were evaluated but mine.
Are there any issues?
I did submit my solution before 11:59pm AoE time

Resource restrictions for training the submissions

Over 4 years ago

@waleedgondal @mohanty
Do we have any restrictions on the evaluation time?

I tried to reproduce your evaluation pipeline on my own kubernetes pod with exactly the same resources and evaluation takes me about 2-3 hours per metric.

It seems perfectly sane to have evaluation as a separate job after training, but would it cause me any problems an later stages if it the whole evaluation happens to take me >10 hours?

Is there any way to pass custom Dockerfile to `aicrowd-repo2docker`?

Over 4 years ago

I faces some problems with building a container for submission using custom environment.yml.
After going over the debug output I see that I could easily fix it if I could change Dockerfile from which image if build from.
In this case in particular it was lacking gcc installed:

  gcc -pthread -B /srv/conda/envs/notebook/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DPSUTIL_POSIX=1 -DPSUTIL_VERSION=563 -DPSUTIL_LINUX=1 -DPSUTIL_ETHTOOL_MISSING_TYPES=1 -I/srv/conda/envs/notebook/include/python3.6m -c psutil/_psutil_common.c -o build/temp.linux-x86_64-3.6/psutil/_psutil_common.o
  unable to execute 'gcc': No such file or directory
  error: command 'gcc' failed with exit status 1

So my question is: is there any way to replace Dockerfile used in build pipeline at least locally, so I could exactly suggest organizers fixes for their Dockerfile?

Is transfer learning allowed?

Over 4 years ago

Well, does it mean it is not forbidden either?

Troubles with submitting starter kit as is

Over 4 years ago

I tried to send a sample submission following https://github.com/AIcrowd/neurips2019_disentanglement_challenge_starter_kit

The container and evaluation worked fine locally but I still got failed label on evaluation step.
My submission tag submission-v0.1 also seems correct.

I tagged @aicrowd-bot in the corresponding issue as instructed to get the debug output.
But is still seems odd to me: is it a common issue or I made a mistake somewhere?

rauf_kurbanov has not provided any information yet.