In the recognition training, though the precision of the training set reaches 90, the precision of the validation set is still 70. How to handle this case? #6017
-
|
In the recognition training, though the precision of the training set reaches 90, the precision of the validation set is still 70. How to handle this case? |
Beta Was this translation helpful? Give feedback.
Answered by
Evezerest
Apr 22, 2022
Replies: 1 comment
-
|
This may be due to overfitting. There are two solutions you can try: (1) Introduce more augmentation methods or increase the probability of augmentation, and the default value is 0.4; (2) increase the 12 decay value of the system. |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
Evezerest
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This may be due to overfitting. There are two solutions you can try: (1) Introduce more augmentation methods or increase the probability of augmentation, and the default value is 0.4; (2) increase the 12 decay value of the system.