during training i got validation loss in negative ?

[xiaoxiao12323]

i got negative validation loss after training ? could you tell me how the model compare images. i have low and high imaes pair as a input images. i consider low as a noisy and high quality images as clean image.

[JK-the-Ko]

As stated in the paper, our proposed loss function is in log scale. Hence, a perfectly optimized model gives you a negative infinite value.
Please refer to the paper.