search

med-air / HarmoFL

[AAAI'22] HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images
86 stars 15 forks source link

FileNotFoundError: [Errno 2] No such file or directory: '../data/prostate/ISBI/Case00.nii.gz' #4

Closed xiaohongri closed 1 year ago

xiaohongri commented 1 year ago

when run test.sh ,there is problem ,how to solve this? FileNotFoundError: [Errno 2] No such file or directory: '../data/prostate/ISBI/Case00.nii.gz'

MeiruiJiang commented 1 year ago

Thanks for your interest in our work. Could you please provide more information? Here are some check steps:

  1. Please make sure you have the data. (if not, please download via this link).
  2. Please check the path. You can change to the absolute path to see if this error will be reproduced.
ToughCookies2020 commented 1 year ago

I ran into the same problem. There are no ISBI and ISBI_1.5 files in the downloaded data set, but there are more BMC and RUNMC files. In addition, I hope that the author can open the code of plotting.

MeiruiJiang commented 1 year ago

I ran into the same problem. There are no ISBI and ISBI_1.5 files in the downloaded data set, but there are more BMC and RUNMC files. In addition, I hope that the author can open the code of plotting.

It seems the original data source changed the file name. Please revise the folder name accordingly. Sorry for the inconvenience.

For the plotting, we refer to this repo for drawing the landscape (https://github.com/tomgoldstein/loss-landscape).

xiaohongri commented 1 year ago

Thanks for your reply, As you said,i have solved this problem, i hope there will be more in-depth exchanges in the future.

--------------原始邮件-------------- 发件人："Meirui Jiang @.>; 发送时间：2023年3月21日(星期二) 下午2:04 收件人："med-air/HarmoFL" @.>; 抄送："肖宏日 @.>;"Author @.>; 主题：Re: [med-air/HarmoFL] FileNotFoundError: [Errno 2] No such file or directory: '../data/prostate/ISBI/Case00.nii.gz' (Issue #4)

I ran into the same problem. There are no ISBI and ISBI_1.5 files in the downloaded data set, but there are more BMC and RUNMC files. In addition, I hope that the author can open the code of plotting.

It seems the original data source changed the file name. Please revise the folder name accordingly. Sorry for the inconvenience.

For the plotting, we refer to this repo for drawing the landscape (https://github.com/tomgoldstein/loss-landscape).

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

cui-yc commented 4 months ago

Why is it wrong for me to use data/prostate directly on this dataset? Does any additional processing need to be done？