-
Notifications
You must be signed in to change notification settings - Fork 862
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
[multimodal] Upgrade preset and update the finetuning example for object detection #3262
[multimodal] Upgrade preset and update the finetuning example for object detection #3262
Conversation
Job PR-3262-cf0f781 is done. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why to change errors to warnings? Are there cases where class number or classes are missing but still work?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Because in test_preset.py
we did not provide sample_data_path
and new DINO model does not have a default CLASSES
value and the test will fail.
if num_gpus is not None: | ||
hyperparameters["env.num_gpus"] = num_gpus | ||
if val_metric is not None: | ||
hyperparameters["optimization.val_metric"] = val_metric |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I can just remove the val_metric here. Later I'll test different val_metric's performance and add it back
Job PR-3262-26f8ab2 is done. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM.
For benchmarking result for three new presets, check internal quip document "Autogluon Object Detection Benchmarking in 0.8.0".
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.