Deep learning - AlexNet neural network re training.

1 visualización (últimos 30 días)
ISURU SAMARAKOON
ISURU SAMARAKOON el 27 de Nov. de 2018
Respondida: ugur arslan el 25 de Dic. de 2019
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?

Respuesta aceptada

Kojiro Saito
Kojiro Saito el 27 de Nov. de 2018
  3 comentarios
Kojiro Saito
Kojiro Saito el 27 de Nov. de 2018
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 el 27 de Nov. de 2018
I will re-train the alexnet again with few more object classes and try the accuracy, anyway thank you so much for your reply.

Iniciar sesión para comentar.

Más respuestas (1)

ugur arslan
ugur arslan el 25 de Dic. de 2019
having same problem. did u getany progress?

Categorías

Más información sobre Image Data Workflows en Help Center y File Exchange.

Etiquetas

Productos


Versión

R2018b

Community Treasure Hunt

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

Start Hunting!

Translated by