Code Monkey home page Code Monkey logo

想请教一下正确的训练步骤: 1.单独训练语言模型pretrain_language_model.yaml,得到最好的语言模型pretrain-language-model.pth 2.然后单独训练视觉模型,得到pretrain-vision-model.pth 3.最后加载前两个与训练模型联合训练train_abinet.yaml 还是直接训练train_abinet.yaml呢? about abinet HOT 2 OPEN

aishangmaxiaoming avatar aishangmaxiaoming commented on August 29, 2024
想请教一下正确的训练步骤: 1.单独训练语言模型pretrain_language_model.yaml,得到最好的语言模型pretrain-language-model.pth 2.然后单独训练视觉模型,得到pretrain-vision-model.pth 3.最后加载前两个与训练模型联合训练train_abinet.yaml 还是直接训练train_abinet.yaml呢?

from abinet.

Comments (2)

FangShancheng avatar FangShancheng commented on August 29, 2024 1

Hi,@aishangmaxiaoming

  1. 论文中汇报的精度是 根据您描述的,1,2,3三步的训练方式
  2. 也可以直接使用train_abinet.yaml,注释两行checkpoint后训练,但这种方式,训练出来的模型效果会稍差些。

from abinet.

aishangmaxiaoming avatar aishangmaxiaoming commented on August 29, 2024

Hi,@aishangmaxiaoming

  1. 论文中汇报的精度是 根据您描述的,1,2,3三步的训练方式
  2. 也可以直接使用train_abinet.yaml,注释两行checkpoint后训练,但这种方式,训练出来的模型效果会稍差些。

谢谢大佬,想问下训练语言模型时,数据集这样:是需要inp 和gt一致,还是不一致呢
image

from abinet.

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.