DeepLung
DeepLung copied to clipboard
DSB stage 2 dataset unzip password wanted
My model is in test stage, I got kaggle stage 2 dataset without unzip password, can someone share it with me? thank you
You may register the kaggle and can get the password.
You may register the kaggle and can get the password.
@wentaozhu I did but stage2 dataset is impossible to download anymore
I think maybe stage 2 is for the final purpose only. Now the competition is finished and there is no access to stage 2.
But I will not close the issue so that other people can help you if they can see this issue. Good luck!
@wentaozhu , Thank you, I already got the stage 2 zip file, so i really want to test my model, just need unzip.txt file, thanks again.
Hello Wentaozhu! Please help me to understant on these.
- Can I train this model by CPU?
- How long it can take to run the process of data preparation?
This is because I tried to run the prepare.py and the file is still in processing for more than one day.
Hello Wentaozhu! I am runing the nodcls/data/extclsshpinfo.py,, but I meet the error No such file or directory: '**/DOI', what the DOI directory contain?
Hello Wentaozhu! I am runing the nodcls/data/extclsshpinfo.py,, but I meet the error No such file or directory: '**/DOI', what the DOI directory contain?
It is LIDC-IDRI dataset https://wiki.cancerimagingarchive.net/display/Public/LIDC-IDRI consisting of dicom images.
Hello Wentaozhu! Please help me to understant on these.
- Can I train this model by CPU?
- How long it can take to run the process of data preparation? This is because I tried to run the prepare.py and the file is still in processing for more than one day.
Yes, you can train it by CPU. Data preparation takes a couple of hours. Try to use 32 CPU kernels.
Hello Wentaozhu! I am runing the nodcls/data/extclsshpinfo.py,, but I meet the error No such file or directory: '**/DOI', what the DOI directory contain?
It is LIDC-IDRI dataset https://wiki.cancerimagingarchive.net/display/Public/LIDC-IDRI consisting of dicom images.
Thanks , can I replace it with luna16 datasets? It is too slow to download the LIDC-IDRI dataset in a server .
Yes. You can. But LUNA16 has no classification label.
Yes. You can. But LUNA16 has no classification label.
I see, thank you very much!
Hello Wentaozhu! Please help me to understant on these.
- Can I train this model by CPU?
- How long it can take to run the process of data preparation? This is because I tried to run the prepare.py and the file is still in processing for more than one day.
Yes, you can train it by CPU. Data preparation takes a couple of hours. Try to use 32 CPU kernels.
Thanks! I did it.
Hello Wentouzhu!
Kindly help me to know, what does tpr, tnr, total pos, and total neg mean??
Hello Wentouzhu!
Kindly help me to know, what does tpr, tnr, total pos, and total neg mean??
Please create a new issue. It does not belong to this issue. Please check the paper for the detail Zhu, Wentao, Chaochun Liu, Wei Fan, and Xiaohui Xie. "DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification." IEEE WACV, 2018. Thank you!
It is the standard TPR, TNR in ROC.