Comments (4)
I think to make mean teacher work, you have to set the consistency_weight to some value. In the mean teacher pytorch webpage, it is set to 100.0. The logit_distance_cost is set to 0.01 for Cifar10 experiment. I believe these are necessary to make mean teacher work.
from mean-teacher.
It looks like that the logit_distance_cost should be set to some positive value only if the student model has two outputs.
And yes, total loss depends on the teacher model only if the consistency_weight is non-zero. But then the accuracy of my minimalistic MNIST implementation is lower compared to a single convnet.
from mean-teacher.
Hi,
So if I understood correctly, your dataset is MNIST with 1000 labeled and 59000 unlabeled examples? And you are using a convolutional network with mean teacher and comparing the results against a bare convolutional network?
Yes, you should set consistency > 0. The best value for consistency may depend on the dataset, the mix of unlabeled/labeled per batch, and other things. A bad consistency cost can lead to worse performance than not using any. Also ema_decay parameter may effect performance a lot. See Figure 4 in the paper for what these look like for SVHN.
At the beginning of the training, the labeled examples are much more useful than the unlabeled examples. If you have a high consistency cost in the beginning, it may hurt the learning. There are two ways around it: either use a consistency ramp-up or use logit_distance_cost > 0 (and yes, two outputs from the network). Also these are hyperparameters that may require tuning.
See also https://github.com/CuriousAI/mean-teacher#tips-for-choosing-hyperparameters-and-other-tuning if you didn't already.
from mean-teacher.
Hi there,
I notice this problem, too. As we known that paper mentioned just 2 kind of loss(class loss and consistency loss) to optimize, what's the situation that student model has 2 output? I saw the difference between the output is that using different fc layer. Is it because representation learning or some stuff?
Thanks a lot!
from mean-teacher.
Related Issues (20)
- Questions about your code HOT 2
- How to use the trained model to do the cifar-10 test? HOT 2
- Question about DataLoader HOT 4
- TypeError: can't serialize tensor(62, device='cuda:0') HOT 5
- ValueError: signal number 32 out of range
- Missing data?
- precision in test is zero all the time
- is alpha set wrong? HOT 1
- The accuracy of validation data is very low
- Blog Post link in the `Readme.md` file is broken
- Problems caused by version incompatibility HOT 1
- Wonderful work, we want to reproduce your results on imagenet, could you provide us your bash with detailed setting?
- Applying approach for NLP problem
- Finally, which one should I take, teacher or student? HOT 2
- The Cifar10 dataset link in Readme in meanteacher/pytorch is lost
- How to train the model with unlabeled data? HOT 3
- How to use this code ?
- Can I use Unet architecture ?
- About two different loss while in training progress HOT 1
- Code problems HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
š 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. ššš
-
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 ā¤ļø Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mean-teacher.