guopengf / fl-mrcm Goto Github PK

Thanks for sharing

Thanks for your sharing! But I do notice that the Unet uses instanceNorm instead of BatchNorm2d and I don't understand why. Is that related to the framework of federated learning?

Can you please let me know how to run it Properly . And configure the dataset properly. I am new to this field ... HELP WILL BE APPRECIATED

Thank You Very Much

Thank you for this great work. I noticed that loss_adv_g will not take effect to the back propaganda because it is detached and re-assigned to a float scalar instead of a variable.

Is it correct?

I downloaded the pre-processing training set of Baidu network disk, but I am prompted to find the verification set at runtime. Is this necessary? Can this data be shared or how can it be modified to avoid this error?

The preprocessed datasets cannot be downloaded successfuly. Could you please upload datasets in BaiduYun?

Thanks for your code, that's a nice job.
You use U-Net as the reconstruction network. Howerver, skip-connections are important part of Unet.
But it seems that you do not use skip connections. Maybe it will cause performance degradation?
I wonder why skip connection is unused for your work.
Thanks!

Thank you for your work, Please ask how do I request the HPKS dataset from Johns Hopkins Hospital？

Hello,

The work is very interesting!
I am familar with MRI reconstruction, but not with federated learning.
Could you provide me some hints on ploting letent feature distribution from different datasets, as shown in Figure 1 d) and e)
Thanks a lot.

Best Regards,
Kingaza

Please share your processed data set (via Google or Baidu Cloud Disk), thank you.For some reasons, it is more difficult to download data from the original site. I will only use the data for research