Giter Club home page Giter Club logo

Comments (2)

hkchengrex avatar hkchengrex commented on June 2, 2024

It doesn't matter.
See this thread: https://discuss.pytorch.org/t/optimizer-step-before-lr-scheduler-step-error-using-gradscaler/92930/3

from stcn.

FlyDre avatar FlyDre commented on June 2, 2024

The code report warnings:warnings.warn("Detected call of lr_scheduler.step() before optimizer.step(). Since I modified part of your network, I want to make sure I don't misunderstand your code. Does self.scaler.step(self.optimizer) (model/model.py line 163) means optimizer.step()in the code?

7f092c665e7e2cf16861f75f3635e01

well, I encounter the same problem ( change ResNet50 to ConvNeXt), and loss1 & loss2 & total_loss turns out to be NaN, could you please show me how you fix it?

from stcn.

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.