NVIDIA / NVIDIA/TensorRT

When converting ONNX to TensorRT, how to let the output shape determined by the input value instead of the input size?

Open
#4,206 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

triaged
Dominant language
C++
Stars
13.4k
Forks
2.4k
Avg merge
5d 3h
Merged PRs (30d)
2

Description

When converting ONNX to TensorRT, how to let the output shape determined by the input value instead of the input size?

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.

Research direction

The issue names no file, test, or entry point. Start by locating the ONNX-to-TensorRT conversion path and its handling of input-dependent output shapes, then determine the expected behavior before assessing whether existing support or a code change is needed. The issue does not specify completion criteria.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.