Comments (5)
This methodology is not MixMatch specific, we used it for all methods. Its purpose was not to stop overfitting but to minimize variance of measurements.
Generally we found the longer you train the better, we trained for 2^16K images (2^26 images) for time constraints (that's roughly a 1000 epochs).
Parameters and settings in our experiments seemed robust across all datasets.
The best suggestion I can offer is to experiment on your data, there's no secret recipe.
from mixmatch.
thanks a lot for your response and advice.
from mixmatch.
Hello again
regarding your previous reply. I am a little confused do you mean 2^16K images is an epoch? If so, why is that (if we think of an epoch as going through the whole dataset once)?
'we trained for 2^16K images (2^26 images) for the time constraints (that's roughly a 1000 epochs)'.
Thank you!
from mixmatch.
cifar10 has 50K images, 2^26/50000 = 1342
the exact number of training epochs.
However since almost every dataset has a different number of samples, to keep the code simple we decide to call an epoch 65536 images (2^16) and share that number for all datasets, so that every experiment on every dataset is trained on the same number of images.
from mixmatch.
Thanks for clear things up!
from mixmatch.
Related Issues (20)
- When will Remixmatch (ICLR'20) be available? HOT 3
- A question about "post_ops" in mixmatch.py HOT 2
- Implemented on other models HOT 1
- What are the most important things to reproduce the result on my own dataset? HOT 2
- Use MixMatch on tabular data. HOT 6
- A question about lambda_u HOT 2
- Is there any reason why you chose to use Beta Distribution? HOT 1
- Reason for ramping up weight of unlabelled loss function(lambda_u). HOT 3
- Comparison of fully supervised models with MixMatch. HOT 2
- how to save the train and test accuracies to disk HOT 2
- question about mixmatch/scripts/create_split.py line113-130
- Working with higher resolution images HOT 1
- Hello, can I use it for multi label classification? If so, what should I pay attention to in the process of tag prediction? For multi label classification, sigmoid is generally used as the loss function. In this case, can you change your loss function to sigmoid? HOT 3
- what is the proper behavior of consistency loss HOT 1
- how to recover performance when doing evaluation HOT 4
- why not using dropout in the wide resnet as done in the wide resnet paper? HOT 4
- In your implementation of Mean teacher, isn't the student model and the teacher model the same? HOT 1
- ModuleNotFoundError: No module named 'libml' HOT 1
- Project dependencies may have API risk issues 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 mixmatch.