How can I improve it?
582383982 opened this issue · comments
First of all, thank you for sharing your code.In the code of the same-resolution vis-ir image fusion, I used your training datasets, test datasets and related parameters, but only a few pairs of the final test results could achieve the effect in your paper.A similar situation occurred after I directly used your model. How can I improve it?
During the training phase, the best results often do not appear when an epoch ends. Sometimes, the results produced during the epoch show a better visual effect. From my point, more attention should be paid to the results produced in the middle rather than those obtained when an epoch ends.
Oh... thank you very much
Now I need a comparative experiment of your method. At the code of the same-resolution vis-ir image fusion, is the model you provided the best training model? If not, could you please provide it?