neheller / kits19

The official repository of the 2019 Kidney and Kidney Tumor Segmentation Challenge
Other
439 stars 179 forks source link

How can we download test data solely? #32

Closed JunMa11 closed 5 years ago

JunMa11 commented 5 years ago

Dear @neheller ,

Thanks for releasing the test data. It seems they are merged with training data. How can we download the interpolated test data solely?

Best, Jun

neheller commented 5 years ago

If you have already cloned the repository for the training data on branch interpolated, you can simply run git pull origin interpolated. If I understand Git LFS correctly, this will download the full test files for the interpolated branch and only small references to test files on the master branch.

JunMa11 commented 5 years ago

Dear @neheller , Thanks for your quick reply. It works, but each downloaded file only has 1KB. What command should I use to get the complete image volume?

image

neheller commented 5 years ago

That's odd. I assume you installed Git LFS to get the data in the first place, correct?

JunMa11 commented 5 years ago

Yes, you are right.

JunMa11 commented 5 years ago

BTW, would it be possible to use google drive to release the test data? @neheller It would be easier to download.

neheller commented 5 years ago

I'm running some tests but I can't seem to reproduce the problem. I'm sorry you're having this issue. I'll look into some alternate methods, but it might take me a day or two to figure something out. Once again, my apologies for the inconvenience.

JunMa11 commented 5 years ago

Hi @neheller , thank you so much for your help. Also, I really appreciate your great contribution to this excellent challenge. Best, Jun

luciaL commented 5 years ago

I have the same problem as you. After git pull origin interpolated, the folders of the test cases are empty. Do you figure out how to make it right?

JunMa11 commented 5 years ago

Hi @neheller , @luciaL I re-download the whole dataset, now it works. best, Jun

luciaL commented 5 years ago

Thank you so much for your reply.