Comments (1)
What I understood is that the author has said the weight parameter will be used to compute the total loss. But when the updation of the centers is being done it is being done without the weight parameter.
Basically, the updates for the centers in this code is nothing but the backpropagation of the mean square error loss.
from pytorch-center-loss.
Related Issues (20)
- question about center loss
- about loss HOT 7
- Dont know how to apply centerloss to my own project HOT 2
- Plots to vizualize HOT 1
- about use own database
- High dimension feature embedding visualization HOT 1
- UserWarning: This overload of addmm_ is deprecated
- Pre-Learned Model
- center loss
- How many classes? HOT 2
- Doesn't anyone think the author's center loss is too complicated? HOT 3
- How to plot the figures? HOT 2
- remember to include The center loss parameters in the optimizer, othewise it will not work HOT 4
- optimizer got an empty parameter list HOT 5
- gradient exploding
- The center loss is very large
- Center loss in small batch multiclass training
- about the feat_dim
- accuracy not increasing
- question about optimizer
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 pytorch-center-loss.