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

[blip2 train bug] about Dongxu 2023/7/21 submit #449

Closed
xingenju opened this issue Jul 24, 2023 · 1 comment
Closed

[blip2 train bug] about Dongxu 2023/7/21 submit #449

xingenju opened this issue Jul 24, 2023 · 1 comment

Comments

@xingenju
Copy link

code runner_base.py: Line 366.
image

The datasets has not been merged here, should call dataloaders() before, or merge datasets before
image
dxli94 added a commit that referenced this issue Jul 24, 2023
@dxli94
[hotfix] #449
34688f3
dxli94 added a commit that referenced this issue Jul 24, 2023
@dxli94
[hotfix] #449 (#450)
c578ed1
@dxli94
Copy link
Contributor

dxli94 commented Jul 24, 2023

Thanks for raising the issue. This happened due to an incorrect branch merging.

I've made a hotfix in c578ed1 that disables before_training() if using epoch-based runner as for now.

Kindly check it out.

@dxli94 dxli94 closed this as completed Jul 24, 2023
maulikmadhavi pushed a commit to maulikmadhavi/LAVIS that referenced this issue May 19, 2024
@dxli94
[hotfix] salesforce#449 (salesforce#450)
61989d7
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
@xingenju @dxli94