Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/17158
Because of Reshape op, batch size can be changed. This diff addresses first order issue raised from multiple batch size system. We need to export different real_batch_size for different max_batch_size input and attach it to the right output.
It also fixes a false exception.
Reviewed By: ipiszy
Differential Revision: D14099541
fbshipit-source-id: 0fa9e86826f417a11d2b5dd2ee60dff64a7ce8c4
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/17046
As we are moving to use bound shape inference, we can remove the awkward fake inference run path and make the code cleaner.
Reviewed By: ipiszy
Differential Revision: D14061501
fbshipit-source-id: b3ace98b3dabef3c3359086a0bb1410518cefa26
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/12900
Workspace sometimes will be populated with input tensors for shape inference but net.external_input() is not a reliable way to tell weights from input in the workspace. We say in some usecases where net.external_input() is empty. In this case, we need to give user an option to provide input hint.
Reviewed By: bddppq
Differential Revision: D10476822
fbshipit-source-id: 1a3fa2df69b959d5b952a7824eba9e6c713f4f07
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/12685
In this diff, we push the fake run of the net into the ONNXIFI transformer, because
1. We cannot do shape inference for every op
2. Since the net has been SSA rewritten, we cannot use shape info from outer workspace directly.
In addition, this diff adds input shape info when querying the `onnxBackendCompatibility` function.
Reviewed By: bddppq
Differential Revision: D10390164
fbshipit-source-id: 80475444da2170c814678ed0ed3298e28a1fba92
Summary:
Since ONNX opset version >5, Reshape changed semantics to take a shape tensor as input instead of relying on `shape` attribute to decide what shape to reshape to. ONNXIFI op has been postponing this change as some of the backends such as TensorRT were not ready. Now that the backends have adopted this semantics, we can remove the legacy mode and output opset version 7 ONNX models.
This change also flushes out some of the bugs and new requirement.
- Converting shape info into int64 tensor
- Fix a bug when we output the shape tensor in the mapped workspace instead of the original workspace
Pull Request resolved: https://github.com/pytorch/pytorch/pull/10848
Reviewed By: houseroad
Differential Revision: D9495121
Pulled By: yinghai
fbshipit-source-id: a6f44a89274c35b33fae9a429813ebf21d9a3d1a
