Combining images and numerical values in a deep neural network

25 ビュー (過去 30 日間)
Luca Ghilardi
Luca Ghilardi 2019 年 7 月 2 日
コメント済み: shlomo odem 2021 年 11 月 14 日
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.
0*Umo-FPkUXDRgXK0L
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?

採用された回答

Gabija Marsalkaite
Gabija Marsalkaite 2019 年 7 月 4 日
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 件のコメント
shlomo odem
shlomo odem 2021 年 11 月 14 日
i have the same problem, did 2021a support multi-input layers?
how can i do this network?

サインインしてコメントする。

その他の回答 (0 件)

カテゴリ

Help Center および File ExchangeImage Data Workflows についてさらに検索

製品


リリース

R2019a

Community Treasure Hunt

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

Start Hunting!

Translated by