Skip to Content
Menú
This question has been flagged
S'ha tancat la pregunta per raó: Question / Code not indented
per Manikandan en 25/10/2025 05:58:13
80 Vistes

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?

Avatar
Descartar
Related Posts Respostes Vistes Activitat
0
d’oct. 25
2
0
d’oct. 25
10
0
d’oct. 25
9
3
de jul. 25
1181
0
d’oct. 25
37