-
Notifications
You must be signed in to change notification settings - Fork 2.9k
[PT FE] Support setting types/shapes for nested structures #25064
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
[PT FE] Support setting types/shapes for nested structures #25064
Conversation
| enabled_transforms, disabled_transforms = get_enabled_and_disabled_transforms() | ||
| if 'ANALYSIS_JSON_PRINT' in enabled_transforms: | ||
| # NOTE that model analysis is performed before applying user's settings (inputs's shapes etc.) | ||
| framework_model = moc_front_end.decode(input_model) | ||
| json_model_analysis_dump(framework_model) | ||
| # a model is not processed further in json analysis mode | ||
| sys.exit(0) |
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.
It was moved unchanged. To preserve behavior and avoid duplication
rkazants
left a comment
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.
please add only changes required for PyTorch and put it under separate if. No need to move helper functions to else
|
@rkazants I moved no helper functions |
Details:
dicts,lists,tuplesas inputs. We unpack them onnormalizestep in PT FE, but this means that those unpacked inputs do not exist before conversion andconvert_modelcan't set shapes/types for them. This PR adds ability forconvert_modelto set shapes/types to any arbitrary input obtained by index or name.Tickets: