Git Product home page Git Product logo

Comments (2)

backseason avatar backseason commented on September 17, 2024 2

Hi,
As the .train() or .eval() mode only affect the BN layers in our network, we freeze these layers during both training and testing.
All the parameters of BN layers are initialized with the imagenet pre-trained model.
For now our model can only run with batch_size=1, there is no reason to learn the params of these layers with so small a batch size.

from poolnet.

YJ-DENG avatar YJ-DENG commented on September 17, 2024

Hi,
As the .train() or .eval() mode only affect the BN layers in our network, we freeze these layers during both training and testing.
All the parameters of BN layers are initialized with the imagenet pre-trained model.
For now our model can only run with batch_size=1, there is no reason to learn the params of these layers with so small a batch size.

Hi,

Thanks for your timely reply, I get the point now

from poolnet.

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.