NVIDIA / NVIDIA/TensorRT

Onnx output differs largely to TRT engine output

Open
#2,691 18 comments 0 reactions 1 assignee View on GitHub

@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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.