Deep learning - AlexNet neural network re training.

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?

Answer 1

[Kojiro Saito]

Here is a transfer learning example using AlexNet. Did you check this?

[ISURU SAMARAKOON]

Hi Kojiro,

Thank you very much for your reply. I refered to the web page but my problem is my training result is always 100% with no errors.I trained only 10 mages. I just want to know whether it is correct or a problem with the network. I've attached snap shot of training process.

(I trained using normal CPU)

[Kojiro Saito]

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]

I will re-train the alexnet again with few more object classes and try the accuracy, anyway thank you so much for your reply.

Answer 2

[ugur arslan]

having same problem. did u getany progress?