Git Product home page Git Product logo

Comments (2)

RabbitWhite1 avatar RabbitWhite1 commented on June 16, 2024 1

These numbers are super helpful! Thanks!!

from ocvp-object-centric-video-prediction.

angelvillar96 avatar angelvillar96 commented on June 16, 2024

Hi Zhanghan,

Below you can find the number of iterations (batches) that the modes were trained for, as well as the number of epochs these iterations correspond to.
Additionally, I report the training time that our experiments took the following using an NVIDIA A6000 with 48Gb

Dataset Model Iters. Epochs Time
Ojb3D SAVi 100k 2000 26h
Obj3D OCVP-Seq 70k 1500 34h
MOVi-A SAVi 150k 2000 120h
MOVi-A OCVP-Seq 50k 300 18h

You can find these numbers and further hyper-parameters in the configuration files.
The number of epochs need not match the exact configuration, since the experiments might have been stopped earlier if the model had already converged.

I hope this answers your question.

Do not hesitate to follow up if you still have any questions.

from ocvp-object-centric-video-prediction.

Related Issues (1)

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.