Odoo is the world's easiest all-in-one management software.
It includes hundreds of business apps:
Been working on an image classification model lately - the training accuracy looks great, but the validation accuracy seems to plateau around 88–90%.
I’ve already tried data augmentation and dropout tuning, but the improvement is marginal.
Curious to know - what’s your go-to approach when your model just refuses to generalise better? Do you usually tweak the architecture, try transfer learning, or focus on data cleaning?
Créez un compte dès aujourd'hui pour profiter de fonctionnalités exclusives et échanger avec notre formidable communauté !
S'inscrire| Publications associées | Réponses | Vues | Activité | |
|---|---|---|---|---|
|
0
oct. 25
|
2 | ||
|
0
oct. 25
|
10 | ||
|
0
oct. 25
|
9 | ||
|
3
juil. 25
|
1186 | ||
|
0
oct. 25
|
37 |
1. Use the live chat to ask your questions.
2. The operator answers within a few minutes.
