How can I use a trained CNN to predict a new image label?

1 vue (au cours des 30 derniers jours)
abich
abich le 16 Mai 2017
Commenté : Kristian Dubrie le 10 Avr 2019
I was applying the following CNN fine-tuning example : https://www.mathworks.com/help/nnet/examples/transfer-learning-and-fine-tuning-of-convolutional-neural-networks.html
The example shows how to fine-tune a pre-trained CNN on letters to classify images of digits. Now i would like to use this new fine-tuned CNN on new images of digits that i have on my computer. How can I do that?
  2 commentaires
Gergely Szépvölgyi
Gergely Szépvölgyi le 24 Sep 2017
Has there been a solution to this since may? I'm facing the exact same problem here.
Kristian Dubrie
Kristian Dubrie le 10 Avr 2019
Any help here?

Connectez-vous pour commenter.

Réponse acceptée

Cam Salzberger
Cam Salzberger le 16 Mai 2017
Hello Abich,
The example you linked shows how to train on a new set of images. I am not a neural networks expert, but if the output you are looking for is the same as the output from the retrained network (digits 0-9), I do not even think you need to replace the final three layers of the network. You can just create the image datastore for your new images, set any options you would like with "trainingOptions", and then call "trainNetwork".
Did you have some specific questions about a particular step?
-Cam
  7 commentaires
abich
abich le 19 Mai 2017
Thank you very much.
An Grg
An Grg le 16 Avr 2018
Modifié(e) : An Grg le 16 Avr 2018
I just wanted to know did it work the classifier? I am having a problem trying to output the probability/predict the testing image.
Thanks and would appreciate reply.

Connectez-vous pour commenter.

Plus de réponses (0)

Catégories

En savoir plus sur Deep Learning Toolbox dans Help Center et File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by