NVIDIA / NVIDIA/TensorRT

The issue of svg generation timeout in the trex tool

Open
#4,562 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Description

I encountered an issue while trying to visualize our model using the trt-engine-explorer tool. During the generation of the SVG output, the process crashes due to the size of the model being too large.

Environment

TensorRT Version:10.4.0

NVIDIA GPU:NVIDIA GeForce RTX 3060

NVIDIA Driver Version:535.230.02

CUDA Version:12.2

Operating System:Linux

Python Version:3.10.14

PyTorch Version:1.13.1+cu117

Baremetal or Container (if so, version): Container

Relevant Files

Model link:
model.graph.json

Steps To Reproduce

I ran a single line of command. It failed to complete and timed out after a while.
Image
I terminated the process right after the timeout occurred.
Image
Eventually, it only produced an invalid result instead of the expected output.
Image

Commands or scripts:python utils/draw_engine.py model.graph.json

Have you tried the latest release?:This seems to have nothing to do with the tensorrt version; it is related to the trex tool.

Can this model run on other frameworks? For example run ONNX model with ONNXRuntime (polygraphy run <model.onnx> --onnxrt):Yes

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

Start with utils/draw_engine.py and reproduce the failure using python utils/draw_engine.py model.graph.json with the attached model.graph.json. Trace the SVG-generation timeout and invalid output, then verify that the command completes and produces a valid SVG for this model.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-graphics, tooling
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.