Summary:
Fix Slice/Select trace arguments. This PR stashes arguments to functions in order to avoid tracing them as constants.
This PR depends on a fix for select op in PR:
https://github.com/pytorch/pytorch/pull/25273
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26549
Reviewed By: hl475
Differential Revision: D17623851
Pulled By: houseroad
fbshipit-source-id: ae314004266688d2c25c5bada2dcedbfc4f39c5b
Summary:
We currently support exporting traced interpolate ops to ONNX.
Scripting interpolate op invokes aten::__interpolate in the Torch IR (instead of aten::upsample_[mode][dim]d), which we do not support yet.
This PR implements the ONNX symbolic for __interpolate() to support exporting interpolate in scripting scenarios.
Related open issue: https://github.com/pytorch/pytorch/issues/25807
Pull Request resolved: https://github.com/pytorch/pytorch/pull/27566
Reviewed By: hl475
Differential Revision: D17817731
Pulled By: houseroad
fbshipit-source-id: e091793df503e2497f24821cf2954ff157492c75
Summary:
Exporting a scripted module to ONNX, with ops like torch.zeros(), fails when the dtype is not specified.
This PR adds support to exporting scripted torch.zeros() ops (and similar ops) without specifying the dtype (dtype will default to float).
Pull Request resolved: https://github.com/pytorch/pytorch/pull/27577
Reviewed By: hl475
Differential Revision: D17822318
Pulled By: houseroad
fbshipit-source-id: b2d4300b869e782a9b72534fea1263eb83744953
Summary:
Exporting torch.select when index = negative one (x[:,-1]) was broken. This PR has the fix in symbolic function for select.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/25273
Reviewed By: hl475
Differential Revision: D17159707
Pulled By: houseroad
fbshipit-source-id: 2c3b275421082758f1b63c1c9b6e578f03ca9f76
Summary:
Running models with inplace operators will change values of input tensors.
Deepcopy input tensors each time to keep the original input tensors intact.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/27186
Differential Revision: D17776598
Pulled By: jerryzh168
fbshipit-source-id: d4808a11185a9ab0d782a62d7d708dfe7e94559c
Summary:
ONNX does not support dictionaries for inputs and output. The reason is that the arg flattening and unflattening does not handle Dictionary types.
This PR adds flattening/unflattening support for dictionaries and strings.
However this feature should be handled with caution for input dictionaries; and users need to verify their dict inputs carefully, and keep in mind that dynamic lookups are not available.
This PR will allow exporting cases where models have dictionnary outputs (detection and segmentation models in torchvision), and where dictionary inputs are used for model configurations (MultiScaleRoiAlign in torchvision).
Pull Request resolved: https://github.com/pytorch/pytorch/pull/25889
Reviewed By: hl475
Differential Revision: D17613605
Pulled By: houseroad
fbshipit-source-id: c62da4f35e5dc2aa23a85dfd5e2e11f63e9174db
Summary:
Currently, we export invalid ONNX models when size() is used with a negative dim.
This PR fixes the issue and allows exporting these models to ONNX (ex: input.size(-1)).
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26436
Reviewed By: hl475
Differential Revision: D17565905
Pulled By: houseroad
fbshipit-source-id: 036bc384b25de77506ef9fbe24ceec0f7e3cff8b
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26778
- Add support for linear and cubic interpolate in opset 11.
- Add support for 1d and 3d interpolate in nearest mode for opset 7 and 8.
- Add tests for all cases of interpolate in ORT tests (nearest/linear/cubic, 1d/2d/3d, upsample/downsample).
Original PR resolved: https://github.com/pytorch/pytorch/pull/24805
Reviewed By: hl475
Differential Revision: D17564911
Pulled By: houseroad
fbshipit-source-id: 591e1f5b361854ace322eca1590f8f84d29c1a5d
Summary:
- Add support for linear and cubic interpolate in opset 11.
- Add support for 1d and 3d interpolate in nearest mode for opset 7 and 8.
- Add tests for all cases of interpolate in ORT tests (nearest/linear/cubic, 1d/2d/3d, upsample/downsample).
Pull Request resolved: https://github.com/pytorch/pytorch/pull/24805
Reviewed By: hl475
Differential Revision: D17330801
Pulled By: houseroad
fbshipit-source-id: 1bdefff9e72f5e70c51f4721e1d7347478b7505b
Summary:
Added support for gelu in symbolic opset9 + op and ORT tests
Pull Request resolved: https://github.com/pytorch/pytorch/pull/24475
Reviewed By: hl475
Differential Revision: D17088708
Pulled By: houseroad
fbshipit-source-id: 9d2f9d7d91481c57829708793d88f786d6c3956f
Summary:
This pass tries to resolve scalar type mismatch issues between input tensors introduced by the implicit type conversions on scalars.
e.g. https://github.com/pytorch/pytorch/issues/23724
Pull Request resolved: https://github.com/pytorch/pytorch/pull/24378
Reviewed By: hl475
Differential Revision: D17088682
Pulled By: houseroad
fbshipit-source-id: 3de710f70c3b70b9f76fd36a7c4c76e168dbc756
Summary:
It appears to be a bug with test_arange, which wasn't revealed with older version of onnxruntime.
TLDR. The test tries to update exported onnx model to accept dynamic sized input, however it is written incorrectly such that the exported model input is still fixed sized. Meanwhile, the version of ort in CI doesn't validate if model input size matches with input data, so this error was not found.
Affecting ci in https://github.com/pytorch/pytorch/pull/25797
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26320
Reviewed By: hl475
Differential Revision: D17406442
Pulled By: houseroad
fbshipit-source-id: a09ad4b925ccbed0b71342f5aaa7878e1c4a5a2d
Summary:
Added support for cumsum in symbolic opset 11 + op and ORT tests
Pull Request resolved: https://github.com/pytorch/pytorch/pull/24476
Differential Revision: D16896780
Pulled By: bddppq
fbshipit-source-id: b52355796ee9f37004c9258f710688ad4b1ae8a2
Summary:
Starting ONNX IR version 4, the initializers in the ONNX graph do not have to be inputs of the graphs. This constraint, which existed in IR version 3 and earlier, was relaxed in IR version 4. This PR provides an API level argument to allow ONNX export with the relaxed constraint of IR version 4, i.e. provides the option to not include initializers as inputs. This allows backends/runtimes to do certain optimizations, such as constant folding, better.
*Edit*: After discussion with houseroad we have the following behavior. For any OperatorExportType, except OperatorExportTypes.ONNX, the current status of export is maintained in this PR by default. However, the user can override it by setting the `keep_initializers_as_inputs` argument to the export API. But when exporting to ONNX, i.e. OperatorExportType is OperatorExportTypes.ONNX, the current status is changed in that by default the initializers are NOT part of the input. Again, the default can be overridden by setting the `keep_initializers_as_inputs` argument.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/23284
Differential Revision: D16459961
Pulled By: bddppq
fbshipit-source-id: b8f0270dfaba47cdb8e04bd4cc2d6294f1cb39cf
Summary:
Without metadata(datatype) for the new output, exporter won't be able to perform implicit scalar datatype casting. This PR covers a large portion of this common issue seen in many exported models, e.g. https://github.com/pytorch/pytorch/issues/23724
Pull Request resolved: https://github.com/pytorch/pytorch/pull/23809
Reviewed By: ezyang
Differential Revision: D16707640
Pulled By: bddppq
fbshipit-source-id: 3de985c6b580b9c9ebaec08085c7443bd8d9c7f8
Summary:
Added a number of opset10 tests from Caffe2 to ORT
Pull Request resolved: https://github.com/pytorch/pytorch/pull/22993
Differential Revision: D16467954
Pulled By: bddppq
fbshipit-source-id: 0b92694c7c0213bdf8e77e6f8e07e6bc8a85170a
