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
[ONNX] Export Unique #25050
[ONNX] Export Unique #25050
Conversation
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.
This looks good
However, while CI failure is unrelated to this diff, it seems to be a flaky ONNX runtime test anyway:
Aug 26 17:28:13
Aug 26 17:28:13 =================================== FAILURES ===================================
Aug 26 17:28:13 _ TestONNXRuntime_opset10.test_elman_tanh_trilayer_forward_no_initial_state_with_batch_first_sequence_lengths_without_dropout _
Aug 26 17:28:13
Aug 26 17:28:13 self = <test_pytorch_onnx_onnxruntime.TestONNXRuntime_opset10 testMethod=test_elman_tanh_trilayer_forward_no_initial_state_with_batch_first_sequence_lengths_without_dropout>
Aug 26 17:28:13
Aug 26 17:28:13 def wrapper(self):
Aug 26 17:28:13 if self.opset_version < min_opset_version:
Aug 26 17:28:13 raise unittest.SkipTest("Skip verify test for unsupported opset_version")
Aug 26 17:28:13 > return func(self)
Aug 26 17:28:13
Aug 26 17:28:13 test/onnx/test_pytorch_common.py:54:
Aug 26 17:28:13 _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
Aug 26 17:28:13 test/onnx/test_pytorch_onnx_onnxruntime.py:938: in f
Aug 26 17:28:13 **extra_kwargs)
Aug 26 17:28:13 test/onnx/test_pytorch_onnx_onnxruntime.py:797: in _dispatch_rnn_test
Aug 26 17:28:13 self._elman_rnn_test(*args, **kwargs)
Aug 26 17:28:13 test/onnx/test_pytorch_onnx_onnxruntime.py:835: in _elman_rnn_test
Aug 26 17:28:13 self.run_test(model, input, batch_size=RNN_BATCH_SIZE, atol=1e-7)
Aug 26 17:28:13 test/onnx/test_pytorch_onnx_onnxruntime.py:78: in run_test
Aug 26 17:28:13 do_constant_folding=do_constant_folding)
Aug 26 17:28:13 test/onnx/test_pytorch_onnx_onnxruntime.py:67: in run_model_test
Aug 26 17:28:13 [np.testing.assert_allclose(out, ort_out, rtol=rtol, atol=atol) for out, ort_out in zip(outputs, ort_outs)]
Aug 26 17:28:13 _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
Aug 26 17:28:13
Aug 26 17:28:13 .0 = <zip object at 0x7f12940eb4c8>
Aug 26 17:28:13
Aug 26 17:28:13 > [np.testing.assert_allclose(out, ort_out, rtol=rtol, atol=atol) for out, ort_out in zip(outputs, ort_outs)]
Aug 26 17:28:13 E AssertionError:
Aug 26 17:28:13 E Not equal to tolerance rtol=0.001, atol=1e-07
Aug 26 17:28:13 E
Aug 26 17:28:13 E Mismatch: 1.59%
Aug 26 17:28:13 E Max absolute difference: 1.6018748e-07
Aug 26 17:28:13 E Max relative difference: 0.01420455
Aug 26 17:28:13 E x: array([[[ 6.488605e-01, 2.153569e-01, 8.207085e-01],
Aug 26 17:28:13 E [ 8.043218e-01, 3.437959e-01, 9.783928e-01],
Aug 26 17:28:13 E [ 8.753051e-01, 6.089818e-01, 9.544484e-01],...
Aug 26 17:28:13 E y: array([[[ 6.488606e-01, 2.153569e-01, 8.207085e-01],
Aug 26 17:28:13 E [ 8.043218e-01, 3.437960e-01, 9.783928e-01],
Aug 26 17:28:13 E [ 8.753051e-01, 6.089818e-01, 9.544485e-01],...
Aug 26 17:28:13
Aug 26 17:28:13 test/onnx/test_pytorch_onnx_onnxruntime.py:67: AssertionError
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.
@dzhulgakov has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
@dzhulgakov Thanks, |
@dzhulgakov merged this pull request in d291935. |
No description provided.