[ONNX] Export Unique #25050
Closed
[ONNX] Export Unique #25050
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dzhulgakov
approved these changes
Aug 27, 2019
There was a problem hiding this comment.
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.
@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. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.