combining two neural networks (net1 is trained & net2 is untrained) in one bigger network

25 views (last 30 days)
I have two shallow neural network models net1, net2.
I have a trained net1. Then I need to connect a net2 to a net1. Hence I treat the combined (net2+net1) as one large net and then train the big net . However, during the second training phase, we only need to update the weights corresponding to net2 (and keep net1 weights fixed). Is it possible in MATLAB? any suggested links or articles to perform this part.

Accepted Answer

Hiro Yoshino
Hiro Yoshino on 10 Jan 2020

More Answers (1)

Greg Heath
Greg Heath on 12 Jan 2020
Just
1. Save the outputs of net1 in a file
2. Use the file to train net2
Greg
  2 Comments
Beatriz Martins
Beatriz Martins on 12 Jan 2020
Edited: Beatriz Martins on 12 Jan 2020
Greg Heath,
I am trying to save the output of a net1 and use it to train net2. However, during training of net1 the trainFasterRCNNObjectDetector function added new layers (initially I have 25 layers and the output of net1 has 35) and I get an invalid network. Do you know how can I solve this problem?
Abdelwahab Afifi
Abdelwahab Afifi on 20 Jun 2020
Edited: Abdelwahab Afifi on 22 Jun 2020
Greg Heath,
more clarification please. I wanna train the bigger networok which combined of (untrained net2 + trained net1)

Sign in to comment.

Categories

Find more on Sequence and Numeric Feature 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!