MATLAB Answers

How to grab intermediate feature maps to do deep supervision

3 views (last 30 days)
zzm oliver
zzm oliver on 27 Apr 2020
Hello. I am doing a semantic segmentation task.I have super high resolution image and its corresponding mask.I downsampled the images so that the data could fit in the gpu memory. My network takes this downsampled image and output a score map. But there's more. My network keeps on upsampling to output a score map of the original super-high resolution. So how do I apply loss both between the intermediate score map and the down-sampled mask and the final score map and the orignal mask.(This is a technique called deep supervision)?
I read the document. There is "forward(dlNetwork)" function available. But that only supports one loss. I want the two loss combined together.

Answers (1)

Srivardhan Gadila
Srivardhan Gadila on 30 Apr 2020
  2 Comments
Srivardhan Gadila
Srivardhan Gadila on 2 May 2020
Refer to Multiple-Input and Multiple-Output Networks for defining network architectures with multiple outputs.
But in case of forward(dlnet), the document of dlnet = dlnetwork(lgraph) says that
"The layer graph must not contain output layers. When training the network, calculate the loss separately.
For a list of layers supported by dlnetwork, see Supported Layers."

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!