-
Notifications
You must be signed in to change notification settings - Fork 278
script for converting retinanet weights from trochvision #2233
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
base: master
Are you sure you want to change the base?
Conversation
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.
Looks good! Just one question.
*args, | ||
**kwargs, | ||
): | ||
# TODO: update presets and remove these old config options. They were |
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.
Have we already updated the preset files? We don't need these shims anymore?
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.
Not yet, but with this we can update the files, I will do that. Yes we will not the extra params
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.
Probably good practice to ditch this change from this PR then. And add this change to the upcoming PR that updates the presets.
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 will update the presets as well as script is ready and I already generated presets just the uploading to Kaggle is pending
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.
Ok! I'll just wait for the preset update on this PR then, either way fine. (but let's avoid removing the compat hack before we add the new presets)
Create a script for converting following torchvison retinanet model checkpoint to keras-hub.
retinanet_resnet50_fpn_coco
retinanet_resnet50_fpn_v2_coco