what is the difference between LayerGraph and DAGNetwork in deep learning?
55 views (last 30 days)
Show older comments
Jack Xiao on 11 Jul 2018
Commented: Royi Avital on 2 Dec 2021
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?
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);
Royi Avital on 2 Dec 2021
One can not use assembleNetwork(layerGraph). Is there a way to validate and initializa a layerGraph without training?
More Answers (2)
the pair of LayerGraph and DAGnetwork remsembles with one of Layer and SeriesNetwork(in my mind)
Handenur Caliskan on 24 Jan 2019
I have the same situtation too. How can we change the trained layergraph to a seriesnetwork or dagnetwork?
Find more on Image 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!