Comments (1)
In fact, we use meta-learning to generate the weights of AdaFM at the very begining. However, we found that this approach brought imbalanced converging speed for the "start" and "end" levels. Specifically, the "end" level, which is with relatively severe degradation, could achieve convergence much faster.
Therefore, we first train a basic model for the "start" level, and then adjust the AdaFM's weights for the "end" level, which has been demonstrated to be efficient. Moreover, since the basic model is fixed, we are free to learn any AdaFM for any "end" level.
from adafm.
Related Issues (10)
- Filter visualization
- how to modify basic.json to train a SRx4 model?
- Could you please upload the supplemental material? HOT 2
- why it returns self.transformer(x) + x not only self.transformer(x)? HOT 1
- Is this a typo in your paper? HOT 2
- why transformer(x)+x? HOT 1
- Why got 'out of memory'?
- ValueError: operands could not be broadcast together with shapes HOT 1
- interpolate_stride=lamda?
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 adafm.