NIH | National Cancer Institute | NCI Wiki  

  • Created by Unknown User (bearceben), last modified on Jul 23, 2020

1) Built pyTorch model that trains and uses a GPU

2) Built Miccai 2020 staging VM to create exact replica of our real challenge to deploy docker submission to.

Planned for next month

1) Hook up real data to GPU VM for docker submissions

2) Try to get issue with V2 sorted out.

Comments

Things that went well:

  • pyTorch model works and I created a docker image housing it and the steps to make the csv submission for the challenge.

Things that could be improved:

  • Having trouble with https and the CodaLab queue system.
MeetingDate
Bi-weekly Meeting #1

 

Bi-weekly Meeting #2

 

Milestones

DescriptionDate
We have a full submission image template for participants to use (docker pull cpmcomps/miccai-2020:training_phase_dl_submission) located here:
https://hub.docker.com/repository/registry-1.docker.io/cpmcomps/miccai-2020/tags?page=1

 

Task

DescriptionResolutionStatusCreation DateClose Date
Create Docker imagestartedcomplete

 

--
Getting NIH badgestartedpending

 

--

Risks

DescriptionMitigationRankStatusCreation DateRealizationClose Date
https with queues seem unlikely. They are supposed to work but right now I can't figure it out and the creator of CodaLab is stumped too.switching the site to http just for docker submission isn't too bad an idea.
in progress

 


--
  • No labels