Combining images and numerical values in a deep neural network
25 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Luca Ghilardi
el 2 de Jul. de 2019
Comentada: shlomo odem
el 14 de Nov. de 2021
I want to combine in a encoder/decoder architecture (like U-Net or FCN) for semantic segmentation both images and numeric values. The images are aerial maps from which I will take random crops to feed the convolutional part of the network, I would also like to add some data in the feature space (like sun inclination) by connecting the fully connected layer of the network with one or more neurons for the numerical part.
My doubts are:
should I use a single input layer that accepts both types of data?
If not, how I can handle the training and datasets with two different input layers?
0 comentarios
Respuesta aceptada
Gabija Marsalkaite
el 4 de Jul. de 2019
Probably simplest way is to add other features as channels. There is example by Uber Engineering where they added gradients for x and y to ease coordinate learning:
https://eng.uber.com/coordconv/
Right now (2019a) Deep Learning Toolbox does not support multi-input layers but we are looking at this and this may change in future releases.
1 comentario
shlomo odem
el 14 de Nov. de 2021
i have the same problem, did 2021a support multi-input layers?
how can i do this network?
Más respuestas (0)
Ver también
Categorías
Más información sobre Image Data Workflows en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!