Comments (2)
Hi,
Thank you for your interest. The proposed loss is for the standard metric learning, so it can be applied for learning the generic features, which can be used for other tasks.
I don't prepare pretrained models since it only costs several hours to train a model on the benchmark data set.
from softtriple.
Got it, thanks !
from softtriple.
Related Issues (16)
- proof of proposition1 HOT 1
- centers = F.normalize(self.fc, p=2, dim=0) what is its purpose? HOT 1
- proposition1 HOT 1
- The BatchNorm layers are not completely frozen HOT 1
- train loss HOT 3
- can you explain the recall@k? HOT 2
- out of memory error HOT 4
- softtriploss param HOT 1
- Code and Paper don't seem to match... HOT 2
- Out of Memory error when training on big number of classes HOT 2
- Clarification on gamma and lambda HOT 2
- MemoryError: Unable to allocate 113. GiB for an array with shape (122994, 122994) and data type float64 HOT 1
- loss is nan HOT 7
- Question - data with unit length HOT 1
- Centers
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 softtriple.