How to grab intermediate feature maps to do deep supervision
4 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
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.
0 commentaires
Réponse acceptée
Srivardhan Gadila
le 30 Avr 2020
The following resources might help you:
3 commentaires
Srivardhan Gadila
le 2 Mai 2020
Refer to Multiple-Input and Multiple-Output Networks for defining network architectures with multiple outputs.
"The layer graph must not contain output layers. When training the network, calculate the loss separately.
Plus de réponses (0)
Voir également
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!