Comments (2)
"I would like to know the reason of using BCE instead of CrossEntropy. Is this critical to Manifold Mixup?"
I don't think it's critical, but I'll check if we have any Manifold Mixup results on these datasets with CrossEntropy instead of BCE.
"Is this also the reason you train 2000 epochs which is much longer than the common training schedules?"
We got improvements with many fewer epochs (definitely with 600 epochs) but the improvement gap grew when we used 2000 epochs.
from manifold_mixup.
Thank you very much for the super fast reply !
from manifold_mixup.
Related Issues (16)
- Error running Semi-supervised Manifold mixup for Cifar10 HOT 3
- More on Reproducing CIFAR10 supervised results HOT 10
- Could you please point out the core novel code? HOT 2
- Error in line 109 of models/resnet.py HOT 1
- Plot Code
- AttributeError: 'CIFAR100' object has no attribute 'targets'
- Does mixup process still work during eval? HOT 2
- Application error HOT 1
- DataParallel Usage HOT 1
- Cannot reproduce CIFAR10 semi-supervised results HOT 26
- Dataparallel issue HOT 2
- Reproducing CIFAR10 supervised results HOT 5
- Question about training epoch? HOT 2
- Making the training process generic for custom models HOT 19
- Question about accuracy during Training HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from manifold_mixup.