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

25 vues (au cours des 30 derniers jours)
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.
  2 commentaires
Xin Yee Tai
Xin Yee Tai le 14 Juil 2020
Could you please share the code to build the neural network on the last photo? Thank you.
Russdsp
Russdsp le 11 Juin 2021
Yes please share code. the green box in the middle doesnt seem like a layer- how is that there?

Connectez-vous pour commenter.

Réponse acceptée

Hiro Yoshino
Hiro Yoshino le 10 Jan 2020
  2 commentaires
Abdelwahab Afifi
Abdelwahab Afifi le 10 Jan 2020
what about connecting two neural networks with each other?
Abdelwahab Afifi
Abdelwahab Afifi le 22 Juin 2020
After training, how can I extract net2 from the big net ?

Connectez-vous pour commenter.

Plus de réponses (1)

Greg Heath
Greg Heath le 12 Jan 2020
Just
1. Save the outputs of net1 in a file
2. Use the file to train net2
Greg
  2 commentaires
Beatriz Martins
Beatriz Martins le 12 Jan 2020
Modifié(e) : Beatriz Martins le 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 le 20 Juin 2020
Modifié(e) : Abdelwahab Afifi le 22 Juin 2020
Greg Heath,
more clarification please. I wanna train the bigger networok which combined of (untrained net2 + trained net1)

Connectez-vous pour commenter.

Catégories

En savoir plus sur Sequence and Numeric Feature Data Workflows dans Help Center et File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by