Comments (4)
Hi @VietHoang1512 .
You can find runs for several methods with full logs for NYUv2 here: https://wandb.ai/geekyrakshit/multi-task-learning?workspace=user-avivnav
While these results are with the SegNet arch., the results are quite similar to MTAN (as we report in the paper).
from nash-mtl.
Thank you for your instant help. I know that the results of SegNet and MTAN are similar but can I ask how big the gap between their learning curves are?
from nash-mtl.
Hi @VietHoang1512.
We don't have such figure that compares MTAN's and SegNet's learning curves, but it should be very easy to create such. Our code supports both models so creating graph like you described should be trivial.
from nash-mtl.
Thank you for your responses, I'm closing the issue now
from nash-mtl.
Related Issues (9)
- MTL for multiple modules? HOT 2
- Mean Rank metric? HOT 1
- Error about IMTLG method HOT 4
- About GradNorm HOT 2
- MT10 Training Code HOT 2
- Thank you for the great repository.If I don't know which parameter is shared and feed all parameters into method, can I get the right result? HOT 3
- Question about large weights HOT 6
- Questions about the property of convergence on theorem 5.4 and 5.5 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 nash-mtl.