FastMRI data set split

[lilygeorgescu]

Hi,

First of all, I would like to congratulate you and your team for your work.

I am also doing research on medical image super-resolution and I would like to test my new method on fastMRI data set. I have seen that the dataset is available online, but I would like to use the same split as you did.

Could you please give me the names of the images that you trained and tested on? I would help me very much.

Best regards,
Iuliana Georgescu

[chunmeifeng]

Hi, please open this link to find the file. https://github.com/chunmeifeng/MINet lilygeorgescu ***@***.***> 于2022年1月17日周一 10:16写道：

…

Hi, First of all, I would like to congratulate you and your team for your work. I am also doing research on medical image super-resolution and I would like to test my new method on fastMRI data set. I have seen that the dataset is available online, but I would like to use the same split as you did. Could you please give me the names of the images that you trained and tested on? I would help me very much. Best regards, Iuliana Georgescu — Reply to this email directly, view it on GitHub <#3>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AR75XN2VJ47DJZOBYS7IVRTUWPM6NANCNFSM5MEERARA> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[lilygeorgescu]

Thank you, I appreciate very much your quick response!

I have seen that in the training file there are 227 rows (the same number specified in your paper), but in the validation file there are 45 rows, but only 24 images are specified in the paper.
Should I test my model on the entire validation split? Did you use a separate set to evaluate your model like validation vs test set?

Thank you,
Iuliana Georgescu

[chunmeifeng]

Yes it's 45 rows lilygeorgescu ***@***.***> 于2022年1月17日周一 14:05写道：

…

Thank you, I appreciate very much your quick response! I have seen that in the training file there are 227 rows (the same number specified in your paper), but in the validation file there are 45 rows, but only 24 images are specified in the paper. Should I test my model on the entire validation split? Did you use a separate set to evaluate your model like validation vs test set? Thank you, Iuliana Georgescu — Reply to this email directly, view it on GitHub <#3 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AR75XN5CANHHIYXLJLDGJW3UWQH25ANCNFSM5MEERARA> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you commented.Message ID: ***@***.***>