onnx / onnx/models

Postprocessing - Ultraface within TensorRT Inference

Open
#461 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
9.8k
Forks
1.6k
PR merge metrics
No merged PRs in 30d

Description

Hello Everyone,

i wrote a Inference within Nvidias TensorRT and got Predictions from my model.
However i dont know how to properly postprocess the predictions to get and draw the right bboxes.
I do know that i have to do some NMS.
Can anyone help and show me which Code-Snippets to use for my specific use-case?
I found an interesting Plugin https://github.com/NVIDIA/TensorRT/tree/master/plugin/batchedNMSPlugin but i dont know how to integrate it.

Model: https://github.com/onnx/models/blob/master/vision/body_analysis/ultraface/models/version-RFB-640.onnx
Inference:
inference_face_detection.txt

Thanks for your help and have a nice day!

Toni

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 inference_face_detection.txt and the linked version-RFB-640.onnx model to identify the prediction outputs. Then read TensorRT's batchedNMSPlugin documentation and examples to determine how it relates to this inference flow. Done would be documented, use-case-specific guidance for postprocessing and drawing the correct bounding boxes.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
18/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.