Giter Site home page Giter Site logo

Comments (3)

sunny2109 avatar sunny2109 commented on June 8, 2024

在RealGANModel模式下,各个损失的loss_weight应该如何设置比较合理

不好意思,回复晚了。
训练的时候,我用到了这些loss: L1, FFT Loss, Perceptual Loss, LDL Loss, GAN Loss
Stage 1: L1 + 0.1*FFT Loss; Stage2: L1 + 0.1*GAN Loss + Perceptual Loss; Stage 3: L1 + 0.1*GAN Loss + Perceptual Loss + 0.5*LDL Loss

from safmn.

harusaju avatar harusaju commented on June 8, 2024

In RealGANModel mode, how should the loss_weight of each loss be set more reasonably?

Hi, did you manage to train the model in RealGANModel mode?

from safmn.

sunny2109 avatar sunny2109 commented on June 8, 2024

In RealGANModel mode, how should the loss_weight of each loss be set more reasonably?

Hi, did you manage to train the model in RealGANModel mode?

Yep, the degradation settings are almost identical to RealESRGAN.

from safmn.

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.