Transfer Learning with Tensorflow's Object Detection API

Question

I am using the Object Detection API and already have a trained model for my specific object classes.

With my task, there will be more and more object classes over time. Since retraining on the combined data sets takes very long, I am interested in a way to only train the pre-trained net on the new data.

I have found this: Retrain Tensorflow Object detection API but since I would need to load the checkpoint on the already trained data and train it again on a combined dataset, which contains the old data, wouldn't that lead to severe over fitting on the old data?

Tengerye · Accepted Answer · 2018-07-27 02:06:17Z

0

No actually, we usually call this trick as fine-tune. The new training dataset containing both old classes and new classes enables CNN to learn a more general representation for all those classes.

answered Jul 27, 2018 at 2:06

Tengerye

2,0042 gold badges31 silver badges47 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Transfer Learning with Tensorflow's Object Detection API

1 Answer 1

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related