Comments (2)
@hbredin I didn't tune it, I found an example for MNIST that worked well with s=7.0, but I will have to modify it for the other tasks.
I understand it's just a scaling factor applied to the difference between the cosines with and without the margin, so my guess is that a bigger scaling will give more importance to small errors.
But again, I'm not certain of this, and I should check the effect of changing it
from similaritylearning.
Thanks. This was also my understanding...
I don't like having too many hyper-parameters...
margin
is probably already quite sensitive...
from similaritylearning.
Related Issues (20)
- Integrate VoxCeleb HOT 3
- Integrate STS Model HOT 1
- Train Contrastive STS model HOT 3
- Integrate SV Model HOT 3
- Trainer Callbacks to Separate Files HOT 1
- Integrate STS Dataset HOT 1
- Train First Speaker Verification Model HOT 10
- STS Cluster Simulation HOT 4
- Triplet STS experiment HOT 2
- ArcFace Speaker Experiment HOT 1
- EER Parallel Validation HOT 1
- Train Softmax STS model
- Significance Test: KL-Divergence and Contrastive loss
- Speaker Verification Training Problem HOT 1
- Test and Compare Speaker Verification Losses
- how to run
- Model Saving HOT 2
- STS Golden Rating plot
- STS Triplets 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 similaritylearning.