Megvii-BaseDetection / Megvii-BaseDetection/YOLOX

Significant Increase in Initialization Time for YOLOX TensorRT Model on NVIDIA-Jetson Nano 4gb

Open
#1,767 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
10.6k
Forks
2.5k
PR merge metrics
No merged PRs in 30d

Description

After converting the YOLOX model to TensorRT, the initialization time on an NVIDIA Jetson Nano 4GB has unexpectedly increased from 1:30 minutes to approximately 5 minutes over a period of time. The pytorch model was converted into tensorRT using the trt module provided by yolox tools that outputs a model_trt.pth file. Is this issue related to caching of yolox?

Contributor guide

No contributing guide indexed for this repository

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 the YOLOX trt module that converts the PyTorch model into model_trt.pth, then reproduce initialization on the NVIDIA Jetson Nano 4GB and compare the reported times. Investigate whether caching explains the increase from about 1:30 to 5 minutes; done means identifying the cause and reporting a reproducible explanation or fix.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
embedded-iot, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
22/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.