Increrasing the validation accuracy

1 view (last 30 days)
new_user
new_user on 4 Jan 2022
Edited: new_user on 18 May 2022
How to reduce the validation accuracy and in the picture the validation curve reached almost 80 but the best vlaidation loss was choosen (52%), is there any way to use plot the best validation accuracy.

Answers (1)

Joss Knight
Joss Knight on 5 Jan 2022
There's no way to do this automatically, but in your case just using the default 'OutputNetwork' setting ( last-iteration ) would do it.
I'm not an expert here but it seems to me that the only way for your loss (which is what you are actually trying to minimize) to be rising while your accuracy is improving is if your network's confidence in the chosen output class is getting worse (but it's still choosing the right one). It may be that you don't really want that network therefore. However, the number of images in your validation set may be a factor here. Perhaps you should increase the size of the validation set?

Categories

Find more on Recognition, Object Detection, and Semantic Segmentation in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!