Giter Site home page Giter Site logo

Finetuning setting about sc6d-pose HOT 4 CLOSED

yuellong avatar yuellong commented on July 20, 2024
Finetuning setting

from sc6d-pose.

Comments (4)

dingdingcai avatar dingdingcai commented on July 20, 2024

How many GPUs are you using for training? The reported results were obtained by training the model on 16 GPUs, which could matter for reproducing the results.

from sc6d-pose.

yuellong avatar yuellong commented on July 20, 2024

I see. What was your batch size? I was using 128 in my case

from sc6d-pose.

dingdingcai avatar dingdingcai commented on July 20, 2024

For a single GPU, the batch_size is set to be 64, so the total batch size should be 64x16=1024

from sc6d-pose.

yuellong avatar yuellong commented on July 20, 2024

Thanks! Is there any other important changes to hyper parameters in addition to learning rate during finetuning?

from sc6d-pose.

Related Issues (6)

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.