Inferior results (FastMRI)

[wafaAlghallabi]

Hello,

Thank you very much for your effort.

I have a question regarding FastMRI results that you've reported in the paper. I trained your Model using the same settings but I got a lower SSIM score on the validation set, 0.8766 (compared to 0.8954).

May I know if you have any idea what could be the reason behind this inferior?

Thanks.

[z-fabian]

Hi wafaAlghallabi,

Can you try downloading our pre-trained checkpoints and see if you get the reported performance? Those models have been evaluated on the official fastMRI test dataset, so they should be working properly.
Let me know how it goes!