Convert ONNX models during import and run import in parallel. #90
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
ScottTodd
commented
Mar 5, 2024
Comment on lines
1
to
8
| module { | ||
| func.func @test_upsample_nearest(%arg0: !torch.vtensor<[1,1,2,2],f32>, %arg1: !torch.vtensor<[4],f32>) -> !torch.vtensor<[1,1,4,6],f32> attributes {torch.onnx_meta.ir_version = 4 : si64, torch.onnx_meta.opset_version = 9 : si64, torch.onnx_meta.producer_name = "backend-test", torch.onnx_meta.producer_version = ""} { | ||
| func.func @test_upsample_nearest(%arg0: !torch.vtensor<[1,1,2,2],f32>, %arg1: !torch.vtensor<[4],f32>) -> !torch.vtensor<[1,1,4,6],f32> attributes {torch.onnx_meta.ir_version = 4 : si64, torch.onnx_meta.opset_version = 17 : si64, torch.onnx_meta.producer_name = "backend-test", torch.onnx_meta.producer_version = ""} { | ||
| %none = torch.constant.none | ||
| %0 = torch.operator "onnx.Upsample"(%arg0, %arg1) {torch.onnx.mode = "nearest"} : (!torch.vtensor<[1,1,2,2],f32>, !torch.vtensor<[4],f32>) -> !torch.vtensor<[1,1,4,6],f32> | ||
| return %0 : !torch.vtensor<[1,1,4,6],f32> | ||
| %0 = torch.operator "onnx.Constant"() {torch.onnx.value = dense<[0.000000e+00, 0.000000e+00, 0.000000e+00, 0.000000e+00, 1.000000e+00, 1.000000e+00, 1.000000e+00, 1.000000e+00]> : tensor<8xf32>} : () -> !torch.vtensor<[8],f32> | ||
| %1 = torch.operator "onnx.Resize"(%arg0, %0, %arg1) {torch.onnx.mode = "nearest"} : (!torch.vtensor<[1,1,2,2],f32>, !torch.vtensor<[8],f32>, !torch.vtensor<[4],f32>) -> !torch.vtensor<[1,1,4,6],f32> | ||
| return %1 : !torch.vtensor<[1,1,4,6],f32> | ||
| } | ||
| } |
There was a problem hiding this comment.
Here's an example where the converter did more than just change the torch.onnx_meta.opset_version.
renxida
pushed a commit
that referenced
this pull request
Jul 18, 2024
Fixes #85 This converts ONNX models to version 17+ as part of importing them, based on the expectation that users will also be able to convert their input programs using the ONNX Version Converter. To make importing test cases faster, this also changes the import script to run in parallel by default.
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.
Fixes #85
This converts ONNX models to version 17+ as part of importing them, based on the expectation that users will also be able to convert their input programs using the ONNX Version Converter. To make importing test cases faster, this also changes the import script to run in parallel by default.