Code Monkey home page Code Monkey logo

Comments (3)

aladdinpersson avatar aladdinpersson commented on May 25, 2024

How many epochs did you run it for? How does the loss behave?

I tried re-training but I do not get this behavior on my PC, although if it is only for the initial epoch I can understand this (as long as the loss is going down). Did you change anything on the setup like learning rate, batch_size, anything?

from machine-learning-collection.

tbass134 avatar tbass134 commented on May 25, 2024

hey aladdin, i was able to fix by just using coping your code over to mine to see the differences. It looks like i had put the removal of the last layer in the inception model in the wrong location. I had it in the forward method in EncoderCNN when it should have been inside the training loop.

The num epochs and learning rate were all the same. This issue occurred after the first epoch. but its working now.

Thanks again!

from machine-learning-collection.

aladdinpersson avatar aladdinpersson commented on May 25, 2024

I'm glad you managed to get it to work! 👍

from machine-learning-collection.

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.