How to add new classes into a pre-trained network?
6 views (last 30 days)
Show older comments
Say I already have a pre-trained network who can classify class A, class B and class C. Is there anyway I can re-train it only using some data from a new class D (instead of using a full dataset that contains data from all four classes), so that the new network is capable of classify both class A, B, C and D? Also wondering if it's achieveable by changing some certain settings during the transfer learning process?
Thanks in advance.
0 Comments
Answers (2)
Gouri Chennuru
on 13 Aug 2020
Hi Da Huang,
You can load the model, train and remove the last layer, change its other neurons and train the network again! This will basically train the the last layer from the beginning.
or, you can also specify the number of classes in the last fully connected layer of your network as the Output size argument.
Hope this Helps!
0 Comments
Farshid PirahanSiah
on 19 Oct 2020
Several ways to add new class to trained model which require just training for new classes.
- Transfer Learning Twice
- Continual learning approaches
* Regularization
* Expansion
* Rehearsal
0 Comments
See Also
Categories
Find more on Image Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!