mbrookhart opened a new pull request #7720: URL: https://github.com/apache/tvm/pull/7720
We've been hitting a lot of errors running models with ONNX, that has led to a lot of piecewise fixes. This is an attempt to fix the importer more broadly by running the tests onnx ships with pip https://github.com/onnx/onnx/tree/master/onnx/backend/test/data/node These files contain an onnx graph, input arrays, and expected outputs, so we can test directly against the canonical onnx tests. This PR provides a method to import these tests as parameterized unit tests, execute them, and skip any we know currently fail. I also fixed a lot of low hanging fruit to reduce the number of unit tests. Future PRs will work to fix the currently skipped tests, and then extend this to GPU. For reference, this is the pytest result on my system, testing against ONNX 1.6, which is what we have in CI: `434 passed, 123 skipped, 83 deselected, 1185 warnings in 32.40s` This adds a lot of tests, but they are all small, so the runtime is actually pretty minuscule, and it improves our ONNX import coverage dramatically. cc @jwfromm @masahi @jroesch @electriclilies @adelbertc -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
