how to train deep learning network with multi-inputs
36 views (last 30 days)
Show older comments
Lina Chato
on 7 Nov 2019
Commented: Hon Wah Yeung
on 4 Aug 2021
Hi I need to train a CNN with two different type of images, so I used the following code
inputSize = [64 64 64 4];
inputLayer = image3dInputLayer(inputSize,'Normalization','none','Name','input');
inputLayer2 = image3dInputLayer(inputSize,'Normalization','none','Name','input2');
when I used analyzeNetwork(lgraph), I got error that should only one input layer be used. So please is there any way I can use multi inputs in the matlab?
Also, if multi inputes is supported in matlab, how can define the two different inputs in the training process ( trainNetwork(dsTrain,lgraph,options);)
I appreciate your advice!
Thanks
2 Comments
Kenta
on 31 Mar 2020
You can use multi-input CNN with "custom training loop" as it is started to be supported from 2019b. The below is an example. I hope it can help you.
Hon Wah Yeung
on 4 Aug 2021
There is an easier way to by-pass it as the inputSize for the 2 inputs are the same.
Just simply stack the 2 inputs channel-wise and use grouped-convolution with number of groups set as 2. Or if you want the learning to be done differently for the 2 inputs, you can create your own layer to split the stacked input into 2 outputs.
Accepted Answer
Sai Bhargav Avula
on 14 Nov 2019
Hi,
You can either use the CombinedDatastore or define a custom layer that can take multiple inputs. For defining a custom layer with multiple inputs you can follow the following link
Hope this helps !
0 Comments
More Answers (0)
See Also
Categories
Find more on Image Data Workflows in Help Center and File Exchange
Products
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!