-1

The learning example of the DeepBelief framework demonstrates how to train a neural network to recognize one object category. The method used for training jpcnn_train() does not have a category label parameter.

However, in the DeepBelief simple example, the given neural network can categorize multiple object categories. Is there a way to do that kind of training through DeepBelief? Or should I look in to Caffe and use that instead as DeepBelief is based on Caffe?

Tunaki
  • 132,869
  • 46
  • 340
  • 423
Senad
  • 166
  • 1
  • 14

1 Answers1

0

Based on their documentation, in particular on a docs for functions jpcnn_train and jpcnn_predict, it does not appear to support multiclass classification for custom labels out of the box. It does seem to support multiclass classification for ImageNet labels.

However, you can train multiple predictors (here's how to train one), one per your custom class, and then choose the class for which the corresponding predictor outputs the highest value.

Ishamael
  • 12,583
  • 4
  • 34
  • 52
  • I can not use that approach because I need a network that can classify multiple object. However, the author has answered me an email and told me to look into libSVM. If I manage to make it work, I will post an answer! – Senad Dec 07 '15 at 11:40