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 retrain the GLIP model on the Object365 dataset #12026

Open
CLL112 opened this issue Nov 4, 2024 · 0 comments
Open

How to retrain the GLIP model on the Object365 dataset #12026

CLL112 opened this issue Nov 4, 2024 · 0 comments
Assignees

Comments

@CLL112
Copy link

CLL112 commented Nov 4, 2024

How to retrain the GLIP model on the Object365 dataset?
Since I made some modifications to the GLIP model, I need to perform some pre-training again to improve performance. I replaced _base_ = [../_base_/datasets/coco_detection.py] with _base_ = [../_base_/datasets/objects365v1_detection.py] in glip_atss_swin-t_a_fpn_dyhead_16xb2_ms-2x_funtune_coco.py to train on Object365. Is this correct? Are any additional steps required?

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

2 participants