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

How to train from scratch? #11788

Open
lionReichl2357 opened this issue Jun 12, 2024 · 1 comment
Open

How to train from scratch? #11788

lionReichl2357 opened this issue Jun 12, 2024 · 1 comment
Assignees

Comments

@lionReichl2357
Copy link

Hi,

i want to train a Deformable DETR head from scratch. I tried to not set 'load_from', but then I get a Error that it can't find the path ''.
When I set it to None I get the same. Moreover I cant set
model = dict(pretrained=...) as it says 'pretrained' is an invalid argument.

So how can I pretrain a head from scratch?

@Cloud65000
Copy link

I'm curious about this too. Though I don't have a straight answer to solve your problem, I suggest setting "justMycode" to False in your configuration file of the debugging process to see more details of the encapsulated class---"runner".
image

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

No branches or pull requests

3 participants