Comments (1)
Hi @xutting123 ,
The contrastive loss can be computed by the cross-entropy loss. In the formula, by setting labels to 0, x[class] (i.e., x[0]) is the positive pair part.
from moon.
Related Issues (20)
- Questions about SCAFFOLD code HOT 2
- The code seems inconsistent with the algoritm in paper HOT 1
- Questions about settings of negative samples HOT 2
- question of compute_accuracy HOT 4
- About the contrastive loss HOT 1
- About the model Resnet50 HOT 3
- About w_i^t in paper. HOT 1
- Why does the program keep showing“Files already downloaded and verified” HOT 6
- Question about dirichlet non-iid HOT 2
- Processing of Datasets HOT 2
- Question about FedAvg code HOT 2
- Questions about the reported test accuracy. HOT 2
- For tinyimagenet, the test acc is very low, 0.009 HOT 4
- Some questions about the metrics. HOT 5
- why we need to requires_grad=True for batch input, which (not sure) may lead to out of memory error. HOT 1
- Time for Training on CIFAR-100 and Tiny-ImageNet HOT 2
- Questions about T-SNE HOT 3
- Same label for positive and negative cases HOT 1
- L2 norm code issue HOT 2
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 moon.