what is the difference between LayerGraph and DAGNetwork in deep learning?

67 views (last 30 days)
Jack Xiao
Jack Xiao on 11 Jul 2018
Commented: Royi Avital about 4 hours ago
I find that the data structure of LayerGraph and DAGNetwork in neural network toolbox have the same contents. So, is there any difference between them?
  3 Comments
Jack Xiao
Jack Xiao on 12 Jul 2018
Do they have the same data structure but not same contents?
DAG:
LayerGraph:
(note:the pictures demonstrate two different networks, so the number of layer and connection are different. here I want to know if for a same network, do they have the same data structure but not same contents?)

Sign in to comment.

Accepted Answer

Maria Duarte Rosa
Maria Duarte Rosa on 25 Feb 2019
LayerGraphs and Layers contain the network architecture (for DAGs and Series networks, respectively). These objects are then passed to trainNetwork for validation and training. LayerGraphs and Layers may have weights or not, but they cannot be used for prediction. One can only call prediction on DAGNetwork and SeriesNetwork objects. These objects contain the validated and trained network.
From R2018b to convert a LayerGraph and Layers object with weights and all the needed parameters to a DAGNetwork/SeriesNetwork one can call assembleNetwork, example:
net = assembleNetwork(layers);
  1 Comment
Royi Avital
Royi Avital 8 minutes ago
One can not use assembleNetwork(layerGraph). Is there a way to validate and initializa a layerGraph without training?

Sign in to comment.

More Answers (2)


Mingrun Wang
Mingrun Wang on 25 Jul 2018
the pair of LayerGraph and DAGnetwork remsembles with one of Layer and SeriesNetwork(in my mind)
  3 Comments
Handenur Caliskan
Handenur Caliskan on 24 Jan 2019
I have the same situtation too. How can we change the trained layergraph to a seriesnetwork or dagnetwork?

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!