Comments (2)
Hi, T-SNE plots (in Figure 4) are obtained as follow:
-
Training the network with the desired method under the target imbalanced ratio, e.g., M2m with \rho=100
-
Then, randomly select N training samples per class which will be plotted using T-SNE. (E.g., N=50 in the paper)
-
Obtaining the "penultimate features", i.e., before the linear classifier, of the selected samples using the trained network
-
The, plot the obtained features using any T-SNE code, e.g., Multicore-TSNE (https://github.com/DmitryUlyanov/Multicore-TSNE)
Best,
Jaehyung
from m2m.
from m2m.
Related Issues (11)
- could be used for detection task HOT 1
- Per-class probablibity being treated as per-sample probability.
- Request for license of M2m
- train M2m HOT 4
- Guidence is needed to reproduce the results ? ? HOT 1
- How to reproduce the results on CIFAR10 and CIFAR100? HOT 1
- Loss function used to train baseline classifier g HOT 1
- Training for celebA dataset HOT 1
- Could you provide the processed CelebA-5 dataset? HOT 2
- Parameter for cifar10/100-r10/100 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 m2m.