Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Train and evaluate on VOC #47

Closed
huohuoR opened this issue Apr 17, 2018 · 4 comments
Closed

Train and evaluate on VOC #47

huohuoR opened this issue Apr 17, 2018 · 4 comments
Labels

Comments

@huohuoR
Copy link

huohuoR commented Apr 17, 2018

Hi, all

I am trying to train the network on VOC dataset and I did:

  1. modify the dataset into ADE format
  2. change the "num_class" to 21
  3. segm += 1: add the ground truth label by 1 both for training and evaluation. (because in your code class 0 didn't count in loss and mIoU)

Am I doing this right?

Any help is appreciated.

@hangzhaomit
Copy link
Collaborator

@huohuoR yes, I think you are on the right track

@huohuoR
Copy link
Author

huohuoR commented Apr 18, 2018

@hangzhaomit Thanks for reply. Looking forward to you update.

@hangzhaomit
Copy link
Collaborator

@huohuoR currently we do not have enough bandwidth to include other datasets, instead we are working to provide better models.

@zhijiew
Copy link

zhijiew commented Apr 26, 2018

@huohuoR
Have you train these model on voc dataset? how about the performance? and what's your meaning of 'modify the dataset into ADE format? could you share your code with me? Thanks a lot!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

4 participants