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.

Sign up for GitHub

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

Jump to bottom

Request for Dataset Proportions in Multitask Model #41

Open
shannon927 opened this issue Dec 10, 2024 · 3 comments
Open

Request for Dataset Proportions in Multitask Model #41

shannon927 opened this issue Dec 10, 2024 · 3 comments

Comments

@shannon927
Copy link

Hi, I have a question regarding the multitask model.
Could you please provide the proportions of all the different training datasets used for this model?
Many thanks！
@CoderZhangYx
Copy link
Collaborator

--dataset "refer_seg||obj365||ade20k||PartImageNet||humanparsing||pascal_part"
--sample_rates "16,4,4,2,2,1"

@shannon927
Copy link
Author

--dataset "refer_seg||obj365||ade20k||PartImageNet||humanparsing||pascal_part" --sample_rates "16,4,4,2,2,1"

Thank you for the detailed response! I have one more question: how is the samples_per_epoch parameter configured for training?
Thanks again for your help!

@CoderZhangYx
Copy link
Collaborator

It's a parameter inherited from codebase indicating item numbers per epoch. Actually, it is useless in our code.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@CoderZhangYx @shannon927