About Augment Images for Training

1 次查看（过去 30 天）
DONGHYUN KIM
DONGHYUN KIM 2019-9-2
回答： Mahesh Taparia 2019-9-20
We know that new augmentation methods are applied randomly at all times.
Insufficient learning, the result is slightly different even though it's the same epoch due to the same data. Can you tell me if this is due to insufficient learning?

请先登录，再回答此问题。

回答（1 个）

Mahesh Taparia
Mahesh Taparia 2019-9-20
Hi,
You can try with all possible data augmentation techniques like flip, rotation, cropping, scaling, adding noise, translation etc. If it won’t work, there may be the chance that your dataset became invariant even after doing data augmentation due to enough data.

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by