How to grab intermediate feature maps to do deep supervision

3 次查看（过去 30 天）
zzm oliver
zzm oliver 2020-4-27
评论： RFC 2023-4-14
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.

请先登录，再回答此问题。

采纳的回答

Srivardhan Gadila
Srivardhan Gadila 2020-4-30
  3 个评论
显示 1更早的评论
Srivardhan Gadila
Srivardhan Gadila 2020-5-2
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."

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

标签

产品


版本

R2020a

Community Treasure Hunt

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

Start Hunting!

Translated by