-
Notifications
You must be signed in to change notification settings - Fork 27.3k
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
Adds GroupViT to models exportable with ONNX #18628
Conversation
The documentation is not available anymore as the PR was closed or merged. |
@regisss hopefully you don't have to make any changes this time to make the tests pass! |
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, you are on fire @unography 🔥
Tests passed.
Pinging @sgugger for final approval |
Feel free to merge if you approve @lewtun |
@lewtun Can you take a quick look at this PR and merge it when you approve? 🙂 |
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.
Thanks for adding this model to the ONNX exporter @unography - as in the OWLViT case, I just have a small comment about the shape of pixel_values
. Otherwise this looks great!
return OrderedDict( | ||
[ | ||
("input_ids", {0: "batch", 1: "sequence"}), | ||
("pixel_values", {0: "batch"}), |
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.
Same comment as in the OWLViT PR: should this be
("pixel_values", {0: "batch"}), | |
("pixel_values", {0: "batch", 1: "num_channels", 2: "height", 3: "width"} }), |
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.
sure, added the change
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.
Thanks a lot for iterating on the dynamic shapes @unography !
This LGTM, so gently pinging @sgugger for final approval
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, thank you @unography!
* groupvit to onnx * dynamic shape for pixel values dim
Adds GroupViT to models exportable with ONNX