Code Monkey home page Code Monkey logo

amos's People

Contributors

jiyuanfeng avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

amos's Issues

about data processing

When processing ct data, run "nnUNet_convert_decathlon_task -i ./DATASET/AMOS22_raw/AMOS22_raw_data/Task01_AMOS_CT
nnUNet_plan_and_preprocess -t 1", you will get two files: nnUNetData_plans_v2.1_stage0 and nnUNetData_plans_v2.1_stage1, but I found that there are 600 files in nnUNetData_plans_v2.1_stage0, including 300 .npz files and 300 .pkl files, which is consistent with the number of CT images, but there are only 326 files in total in nnUNetData_plans_v2.1_stage1. Is this normal?

Where is the code?

Would you mind introuducing whether and when would you release the training and inferfence codes?
Many thanks.

about training time

Hi could you please tell me how long it takes for training on ct task. I trained it on TITAN with 12 G memory, and it takes about 11 days which is too long

transfer learning from AMOS dataset to KiTS dataset

Great code and very impressive paper. Thank you very much!

I am writing to consult problem with transfer learning from AMOS dataset to KiTS dataset.

In the table 3 of the paper, you pre-trained with AMOS, then apply it on KiTS dataset, finally, you got 88.33 dice score, I found it is very interesting, so I tried the same thing, but only got 65.54 dice score. I don't know what is went wrong, the following is the potential problem:

  1. The two dataset has different axis ordering, AMOS dataset is (z,y,x), while KiTS is (x,y,z). Did you doing anything to preprocess it or you just ignore it?
  2. The two dataset has different voxel spacing, how did you preprocess them to become same target spacing?

Hope to get some response from you. Thank you~

dataset license

Hello,

Thanks for your work.
Could you please tell me what is the latest dataset license?

  • CC BY-NC-SA license?
  • Creative Commons Attribution 4.0 International license?
  • Or other licenses?

About submitting test sets after the competition

Thank you so much for the valuable abdominal multi-organ data and for hosting the AMOS2022 competition.
I am currently training with the Amos 2022 data set.
Could you tell me how to submit the test set after the competition?
image
I know to submit the test set file on this page, may I ask what the submission file is TEAMNAME.tar.gz?
But obviously not, it will alert me to file format errors, so I am very anxious that you will see my question and reply as soon as you can.
Finally, thank you very much for your hard work!

Regarding the code

Hi,
Excellent dataset and paper. I'd like to use AMOS for my research and want to reproduce some results in the paper. But I find that codes are removed from this repo. I would greatly appreciate it if you could provide some code to help me get started.

Best.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.