NIH | National Cancer Institute | NCI Wiki  

Versions Compared

Old Version 1

changes.mady.by.user Unknown User (bearceben)

Saved on

compared with

New Version Current

changes.mady.by.user Unknown User (bearceben)

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

1) Learn the basics of pyTorch in order to build sample submission that exercises the GPU.

2) Update form with edits from Ulli and Carolyn. 

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 to3) Started working on CodaLab V2 and got Miccai 2020 challenge loaded into it. There are still some issues as during a submission it never registers a pass.

Planned for next month

1) Implement Docker image submission with real inference implemented on GPU remote machine.

2) Make edits to PR website as needed.

Hook up real data to GPU VM for docker submissions

2) 3) Try to get issue with V2 sorted out.

Comments

Things that went well:

  • pyTorch is approachable model works and I 'm getting the hang of it. Just trained my very first model. Essentially running this on the path\rad data is all we need.Met with Eric Carmichael from CKCollab (https://www.linkedin.com/in/ericatckcollab/). He is the author of CodaLab V1 and V2 and runs a 6 person company at https://ckcollab.com/created a docker image housing it and the steps to make the csv submission for the challenge.

Things that could be improved:

  • My current understanding of pyTorch
  • Identifying proper Azure OSes that have GPU enabled software and identify which GPUs run on themHaving trouble with https and the CodaLab queue system.
MeetingDate
Bi-weekly Meeting #1

14 May  

Bi-weekly Meeting #2

28 May  

Milestones

 
DescriptionDate
Trained my first model in pyTorch

 

Got Miccai 2020 loaded into V2 of CodaLab
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

 

Image Added

Task

DescriptionResolutionStatusCreation DateClose Date
Create Docker imagestartedpendingcomplete

13 May  

--
Getting NIH badgestartedpending

 

--

...

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

 


--