Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Constant data-spacing #1

Closed
neheller opened this issue Mar 16, 2019 · 6 comments
Closed

Constant data-spacing #1

neheller opened this issue Mar 16, 2019 · 6 comments

Comments

@neheller
Copy link
Owner

React with a 馃憤 if you would find useful a separate branch(es) with the data and labels transformed to fixed pixel_width and slice_thickness.

@neheller
Copy link
Owner Author

neheller commented Apr 3, 2019

This is in progress and will be part of the April 15 release. Our plan is to interpolate to the overall medians of slice thickness and pixel width. That will be a slice thickness of 3.0 mm and a pixel width of 0.781625 mm.

The testing set release will also include a copy of the data transformed to this spacing. For evaluation, participants will be allowed to submit predictions either in original spacing or in median spacing.

@neheller
Copy link
Owner Author

Unfortunately we're going to have to push this back to April 22 to finish ironing out the kinks with the interpolation method. Since we will be evaluating teams based on these labels, we want to make sure we hold them to the same standard as the labels in original spacing, and right now a handful of cases are exhibiting some pesky artifacts. Thanks for your patience while we work through them.

The amended labels in original spacing will be released today as planned.

@neheller
Copy link
Owner Author

The data at constant spacing has been pushed to a new branch called interpolated. If you've already cloned the repository, you can use the following commands from the repository root

git fetch
git checkout origin/interpolated

If you have not yet cloned the repository and you would only like to download only the interpolated data, you can use

git clone -b interpolated --single-branch https://github.com/neheller/kits19

On my machine, the interpolated data occupies roughly 50GB.

Enjoy!

@JunMa11
Copy link

JunMa11 commented Apr 23, 2019

Hi @neheller ,
Thanks for providing the interpolated data.

I have installed git-lfs, but the downloaded data is not complete. Each data only has 1 KB.

download error

Would it be possible for you to give me some insights on what's wrong with my download?

@neheller
Copy link
Owner Author

Interesting, I'm not a windows user so I'm not really sure what the problem is here. Can anyone else shed some light?

When I originally tested the LFS functionality on Windows I used the GitHub GUI and it worked without issue.

@JunMa11
Copy link

JunMa11 commented Apr 23, 2019

Black magic!
I try another windows computer, it works! But the first computer still does not work even by github bash.
Anyway, I can access the interpolated data.
Thanks for your quick reply. @neheller

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants