Comments (2)
Hi @dingusagar, thanks for asking!
During the inference, we use SimilarityModel instance that is composed of an Encoder
and an EncoderHead
--not simply Encoder
.
So if we choose to freeze Encoder
then EncoderHead
is still trainable to hopefully boost the performance as a part of our SimilarityModel
.
Hope it helps.
from quaterion.
Okay got it. I think I missed to read about SimilartyModel class in the docs. Thanks for the reply.
from quaterion.
Related Issues (20)
- Badges in readme
- [BUG] ImportError: cannot import name 'PossibleUserWarning' from 'pytorch_lightning.utilities.warnings' HOT 2
- [bug] broken links in documentation
- [docs] Add README.md to `examples` HOT 2
- Implement cross-batch memory for losses HOT 2
- PyTorch Lightning's Stochastic Weight Averging callback causes infinite recursion HOT 4
- Add Quaterion to conda channel
- Add support for soft margin variant of triplet loss
- Inplace computation error with XBM HOT 10
- Reduce amount of memory required by mining strategies HOT 2
- Implement multi-objective loss HOT 2
- Improve evaluation procedure for extensive results HOT 1
- Training error using multiple GPUs HOT 1
- How to load encoder HOT 3
- error while serving the model HOT 5
- No Python 3.9/3.10 support of quaternion and quaternion-models HOT 2
- Feature: FastAP Loss Function HOT 2
- Improvement: Update internal `torch.norm` calls to `torch.linalg.norm` HOT 2
- Support for Python 3.10+ HOT 4
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 quaterion.