Onnx output differs largely to TRT engine output
Open
@zerollzeng is already working on this.
Since Feb 18, 2023.
triaged
- Dominant language
- C++
- Stars
- 13.4k
- Forks
- 2.4k
- Avg merge
- 5d 3h
- Merged PRs (30d)
- 2
Description
Description
I have an onnx model, whose output has beed verified to be almost identical with my original PyTorch model.
After I convert it to tensorrt engine, the output changes too much. I don't know if there is any tool I can use to debug and locate the place where error produced between onnx and trt?
It shows the absolute error is ~4.6 that large.
Also refer to https://forums.developer.nvidia.com/t/onnx-output-is-differs-largely-to-trt-engine-output/243278
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.