How to add new classes into a pre-trained network?
7 次查看(过去 30 天)
显示 更早的评论
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 个评论
回答(2 个)
Gouri Chennuru
2020-8-13
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 个评论
Farshid PirahanSiah
2020-10-19
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 个评论
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!