Giter VIP home page Giter VIP logo

segmentation's People

Contributors

gwencong avatar

Stargazers

avatar avatar

Watchers

avatar

segmentation's Issues

Questions about offsets, net-scale-factor in DeepStream config

Hello
Thank you for providing an example to run on the DeepStream pipeline with a model trained in PaddleSeg!
I have a question while using it.
In PaddleSeg, normalize uses mean and std, which are used in the default Imagenet
Then, I think we should refer to the forum and GitHub below and set it up in deepstream config as below

net-scale-factor=0.017352074
offsets=123.675;116.28;103.53

Is there a reason why you did it differently?

https://forums.developer.nvidia.com/t/pytorch-normalization-in-deepstream-config/158154/7
https://github.com/NVIDIA/retinanet-examples/blob/main/extras/deepstream/deepstream-sample/infer_config_batch1.txt

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.