Relax constraint on subgraph input/output type and shape #2009
Conversation
This file contains hidden or 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
gramalingam
reviewed
May 8, 2019
gramalingam
reviewed
May 8, 2019
linkerzhang
reviewed
May 9, 2019
houseroad
reviewed
May 9, 2019
2 tasks
facebook-github-bot
pushed a commit
to pytorch/pytorch
that referenced
this pull request
Jun 3, 2019
Summary: ~~This is work in progress due to its dependency on multiple pending PRs.~~ - [x] ONNX: Relax constraint on subgraph input/output type & shape check. onnx/onnx#2009 - [x] PyTorch: Add infra to test_pytorch_onnx_caffe2.py to test ScriptModule models. #20256 This PR should partially resolve #17531. However, ideally we shouldn't need to put cast(and reshape) node to help the conversion for loop condition. - Added cast node for condition values before entering loop node. The ONNX spec only accepts Bool type, while in PyTorch if the condition value is an output from other node it could potentially have any integral type. - Tidying up the exported ONNX loop subgraph input type & shape. According to ONNX spec, input "M" is exported as 0-d scalar tensor with type int64. input "Cond" is exported as incomplete tensor of type Bool without shape information. This is because through out the iteration, the rank of condition value is dynamic, either 0-d or 1-d, as long as it holds a single value. Pull Request resolved: #20445 Differential Revision: D15534188 Pulled By: houseroad fbshipit-source-id: d174e778529def05ee666afeee4b8fb27786e320
hariharans29
pushed a commit
to hariharans29/onnx
that referenced
this pull request
Aug 15, 2019
* Relax constraint on subgraph input/output type and shape * use is_main_graph in CheckerContext * create copy of CheckerContext for subgraph * fix nested_graph test case
jcwchen
pushed a commit
to jcwchen/onnx
that referenced
this pull request
Sep 23, 2020
* Relax constraint on subgraph input/output type and shape * use is_main_graph in CheckerContext * create copy of CheckerContext for subgraph * fix nested_graph test case
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.
In many cases, it is not obvious to know the shape information of inputs/outputs for the subgraph, especially in models where dynamic shape is involved. This PR relaxes this check for subgraph.