mbrookhart commented on a change in pull request #7747:
URL: https://github.com/apache/tvm/pull/7747#discussion_r601973492
##########
File path: tests/python/frontend/onnx/test_forward.py
##########
@@ -4278,6 +4278,33 @@ def test_wrong_input():
relay.frontend.from_onnx(model, shape=wrong_shape_dict)
+def test_aten():
+ torch.set_grad_enabled(False)
+
+ def _convert_to_onnx(model, inputs):
+ file_name = "{}.onnx".format("aten_model")
+ torch.onnx.export(
+ model, inputs, file_name, export_params=True, verbose=False,
opset_version=10
+ )
Review comment:
Can we assert that this actually contains the expected aten model? What
conditions mean that pytorch instead exports a valid onnx graph?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
