Cardiac MR testing set

[Yongze]

Hi,
In the supervised training, if I train the model in mr training set (in .tfrecord), and then test in testing set (in .tfrecord), the performance is better than I test the model in the testing set (in .nii.gz) with a large margin. But both testing set have the same images and I expect the performance should be close.

Hope you can explain a little bit for me. Much appreciated in advance.