How to use ImageNet Database in Matlab for object classification or recognition? I didn't find any tutorial which could practically tell me how to train images on ImageNet database and classify the objects.


closed as too broad by jojek, lennon310, Batman, Matt L., Peter K. Aug 12 '15 at 12:12

Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • $\begingroup$ Welcome to DSP.SE! We've closed this question because there are any number of ways to do what you're asking, but we'd need more details to be able to help in any but a LMGTFY sense. $\endgroup$ – Peter K. Aug 12 '15 at 12:17
  • $\begingroup$ This question is very broad. Just add deep learning / convolutional networks so that it makes sense. $\endgroup$ – Tolga Birdal Aug 12 '15 at 20:07

Use MatConvNet. They have samples for image-net classification, such as this. Pre-trained models already exist. You could also train on your own.

  1. Check cnn_imagenet function in MatConvNet. You will find it useful.
  2. There are tutorials. For example this one.
  • $\begingroup$ Your answer is somehow useful. But i want to use Stanford's ImageNet Database, the largest annotated image dataset. $\endgroup$ – Prem Aug 11 '15 at 10:20
  • $\begingroup$ It could work on this dataset. I updated my answer. $\endgroup$ – Tolga Birdal Aug 11 '15 at 11:46

Not the answer you're looking for? Browse other questions tagged or ask your own question.