Skip to content

Import squeeze from symbolic_opset11 #4230

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.

Sign up for GitHub

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

Merged
merged 2 commits into from
Aug 12, 2021
Merged

Import squeeze from symbolic_opset11 #4230

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b370e68
Import squeeze from symbolic_opset11
jiafatom Jul 29, 2021
5f16fb2
Merge branch 'master' into squeeze_11
NicolasHug Aug 12, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion torchvision/ops/_register_onnx_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,8 @@
def _register_custom_op():
from torch.onnx.symbolic_helper import parse_args, scalar_type_to_onnx, scalar_type_to_pytorch_type, \
cast_pytorch_to_onnx
from torch.onnx.symbolic_opset9 import select, unsqueeze, squeeze, _cast_Long, reshape
from torch.onnx.symbolic_opset9 import _cast_Long
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the PR @jiafatom , I'm wondering, why leaving this one to opset9?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There is no _cast_Long in torch.onnx.symbolic_opset11. Not every function can be found in upper opsets torch.onnx.symbolic_opset11. We only updated if there is spec change.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@NicolasHug Can we merge the PR? thanks!

from torch.onnx.symbolic_opset11 import select, squeeze, unsqueeze

@parse_args('v', 'v', 'f')
def symbolic_multi_label_nms(g, boxes, scores, iou_threshold):
Expand Down