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

Question

0 个投票

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 个评论
显示 1更早的评论隐藏 1更早的评论

Karthiga Mahalingam 2018-7-11

A LayerGraph is used to specifically describe layout of the layers of a DAG network. It has methods to play around with the layer structure such as addLayers, connectLayers. removeLayers etc. A DAGNetwork is the neural network model as a whole and not just the layers. Its' methods involve playing around with the model like predict, classify, activations etc. In short, you'd be using layerGraph to specify a DAGNetwork but there is much more to it like training it etc.

Jack Xiao 2018-7-12

image.png

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?)

请先登录，再进行评论。

请先登录，再回答此问题。

Follow Question

Answer 1

Maria Duarte Rosa 2019-2-25

1 个投票

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);