Comments (5)
I set d_learning_rate = 1e-3 and c_learning_rate = 1e-5 can get a good result.
source only <<<
Avg Loss = 1980.854672080592, Avg Accuracy = 75.000000%
domain adaption <<<
Avg Loss = 97.09941973184284, Avg Accuracy = 92.903227%
from pytorch-adda.
See #29
from pytorch-adda.
I got accuracy = 8 after domain adaptation……
from pytorch-adda.
Did you solved this issue ? I'am also facing low DA accurcay
from pytorch-adda.
I think what causes the low adaptation accuracy is that the class labels are swapped by the target encoder. This makes sense because it is an unsupervised task and the target encoder didn't see the class labels.
I've used this code on 2D data:
https://github.com/mashaan14/ADDA-toy
You can see in the attached image that the target encoder separates the classes well. But the class labels were swapped.
from pytorch-adda.
Related Issues (20)
- 0% accuracy with pytorch >= 0.4.0 HOT 4
- Criterion problem HOT 2
- Pretrain+Finetune results?
- Anybody visualized feature adaptation?
- Two feature maps output from discriminator?
- Adaptation leads to lower precision. HOT 7
- Question about the loss HOT 1
- I can't download
- I can't download
- Questions about zero_grad()
- ERROR!!! HOT 1
- error about mnist data shape HOT 7
- d_loss and accuracy HOT 8
- The adaptation does not work HOT 1
- something about eval
- Question about the USPS dataset HOT 2
- RNN network invalid HOT 1
- why in adapt.py line 91 label_tgt = make_variable(torch.ones(feat_tgt.size(0)).long())? I think label_tgt = make_variable(torch.zeros(feat_tgt.size(0)).long()) HOT 2
- How to adapt when the dataset of the target domain is much smaller than source domain
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 pytorch-adda.