Megvii-BaseDetection / Megvii-BaseDetection/YOLOX

check a speed of model

Open
#1,500 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

Hi, I'm currently using a model yolox-s for mobile.
I want to compare the speed between original yolox-s model and my own trained based on yolox-s.
So, I compared with them with onnxruntime demo and checking time in colab like below.

%load_ext autotime
python3 onnx_inference.py -m <ONNX_MODEL_PATH> -i <IMAGE_PATH> -o <OUTPUT_DIR> -s 0.3 --input_shape 640,640

Is it correct way to compare execution time for model?
Is there any suggestion to benchmark a model? like checking GFLOPs, fps or latency.

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 referenced onnx_inference.py command and the Colab timing setup, then review the repository's existing model and deployment documentation for benchmarking guidance. A useful outcome would be a documented, reproducible way to compare the original and trained YOLOX-s models using latency, FPS, or GFLOPs.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Documentation
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.