Using pretained model in our code #712
-
Hi, I was wondering how to easily use a pretained model (Task005_Prostate) in the code in an easy way. I would like to extract some feature maps of intermediate layers and reuse the latent representation of the bottleneck of one of UNet. I am not very familiar with the framework and you could be of great help. |
Beta Was this translation helpful? Give feedback.
Answered by
FabianIsensee
Aug 25, 2021
Replies: 1 comment
-
You should just follow the code of nnUNet_predict. You can replicate it in your script and then access the model. In order to gett access to the feature maps you will need to modify th Generic_UNet |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
FabianIsensee
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
You should just follow the code of nnUNet_predict. You can replicate it in your script and then access the model. In order to gett access to the feature maps you will need to modify th Generic_UNet