We evaluated images from undersampled data using a U-Net with common metrics (SSIM and NRMSE) and with a model for human observer detection, the sparse difference-of-Gaussians (S-DOG). We also studied how the results vary when changing the loss function and training set size. We saw that the S-DOG model would choose an undersampling of 2X while SSIM and NRMSE would choose 3X. In previous work, human observers also chose a 2X acceleration. The S-DOG model led to the same conclusion as the human observers. This result was consistent with changes in training set size and loss function.