Git Product home page Git Product logo

Comments (3)

holynski avatar holynski commented on August 17, 2024

It was trained for 22,000 steps.

from instruct-pix2pix.

dilinwang820 avatar dilinwang820 commented on August 17, 2024

Hello @holynski, does the 22,000 steps refer to the number of optimizer steps or the number of training batches? As in your training config, the gradients are accumulated between every 4 batches, that amounts to a 4x difference. Thank you!

from instruct-pix2pix.

XiaoyuShi97 avatar XiaoyuShi97 commented on August 17, 2024

Hi. I am also confused about the training steps. The paper says 10000 steps with batchsize 1024. But the default setting is batchsize 32*8=256? And the epoch number is 2000, which is too large?

from instruct-pix2pix.

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.