Skip to content

Add tests for ONNX function #199

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

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Add tests for ONNX function #199

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
34 changes: 34 additions & 0 deletions onnxoptimizer/test/function_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
import io
import onnx
import onnxoptimizer
import pytest
import unittest

try:
import torch
import torchvision as tv

has_tv = True
except:
has_tv = False


@pytest.mark.skipif(not has_tv, reason="This test needs torchvision")
def test_function_preserved():
with io.BytesIO() as f:
module = tv.models.resnet18()
torch.onnx.export(
module,
(torch.ones([1, 3, 224, 224], dtype=torch.float32), ),
f,
opset_version=15,
export_modules_as_functions={
Copy link
Member

Choose a reason for hiding this comment

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

This option is deprecated in torch 2.8. I would consider directly creating an onnx function and not relying on PyTorch. You may use onnx-ir to simplify the creation code if you like.

Copy link
Member Author

Choose a reason for hiding this comment

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

Thank you for the suggestion. I'll check that also.

torch.nn.BatchNorm2d,
torch.nn.Conv2d,
}
)

model = onnx.load_model_from_string(f.getvalue())
opt_model = onnxoptimizer.optimize(model)
assert len(model.functions) > 0
assert len(model.functions) == len(opt_model.functions)
Loading