Deep learning - AlexNet neural network re training.

5 次查看(过去 30 天)
I'm using Alexnet to detect only one class of objects. I have re - trained alexnet with only one object class pencil over 100 pencil images. The training result is always 10020with no errors. When I'm using it for detection it gives 100 How to re-train this CNN accurately?

采纳的回答

Kojiro Saito
Kojiro Saito 2018-11-27
  3 个评论
Kojiro Saito
Kojiro Saito 2018-11-27
I think it's because there's only one label "pencil". Any picture will be labeled as pencil. If you prepare images of other labels, the accuracy will be getting more accurate.
ISURU SAMARAKOON
ISURU SAMARAKOON 2018-11-27
I will re-train the alexnet again with few more object classes and try the accuracy, anyway thank you so much for your reply.

请先登录,再进行评论。

更多回答(1 个)

ugur arslan
ugur arslan 2019-12-25
having same problem. did u getany progress?

类别

Help CenterFile Exchange 中查找有关 Image Data Workflows 的更多信息

标签

产品


版本

R2018b

Community Treasure Hunt

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

Start Hunting!

Translated by