GithubHelp home page GithubHelp logo

Comments (4)

thangt avatar thangt commented on July 22, 2024

The Instance Segmentation gave all the objects in the scene a mask id which include those distractors or background objects. You can keep a list of the annotated objects that you care about and ignore all the other object mask.
Do you need to control the color of the background or you just want to understand how things work?

from dataset_synthesizer.

plasma-vision avatar plasma-vision commented on July 22, 2024

I thought it might be something like that.
I'm just trying to understand how it works.
I figured out that I can map the instance_id to the mask color using the algorithm ConvertInt32ToVertexColor defined in NVSceneCaptureUtils.cpp.
I assume that is a good way to figure out which particular color of mask refers to a specific object instance. If that is so, I don't need to worry about the background color.
Many thanks for your help.

from dataset_synthesizer.

thangt avatar thangt commented on July 22, 2024

Yes, that function is the one we use to convert the id to the color on the segmented image.
As I mentioned before, most of the time you only need to care about the annotated objects, all the other can just be considered as noises and be ignored when you do training.

from dataset_synthesizer.

smitheric95 avatar smitheric95 commented on July 22, 2024

Hey @thangt, I know this is a very old thread, but I'd like the instance masks to have a background value of 0 and flying distractors to not be visible in the .is.png images.

Do you know how I can achieve this?

from dataset_synthesizer.

Related Issues (20)

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.