Replies: 1 comment
-
| Hi @AnikaP How about starting with MMSegmentation library? They support various Timm models as backbone so that you can freely change the backbone network architecture as your purpose. Thank you. Hankyul. | 
Beta Was this translation helpful? Give feedback.
                  
                    0 replies
                  
                
            
  
    Sign up for free
    to join this conversation on GitHub.
    Already have an account?
    Sign in to comment
  
        
    
Uh oh!
There was an error while loading. Please reload this page.
-
Hi, thanks for the work you're doing!
I'm currently looking into image segmentation models (like eva) and have a hard time understanding the training pipeline (using the train.py script). In my understanding the dataloader and train script are designated for classification purposes? Any input how to train for segmentation to help me get started would be appreciated!
Beta Was this translation helpful? Give feedback.
All reactions