Comments (7)
The branch has been merged into main.
from uno.
Hi,
Thanks for your interest in our work.
I don't remember exactly how I implemented it but for sure you will need to:
- do not concat here
Line 155 in 1d7811f
- the shape of this tensor will also change
Line 164 in 1d7811f
- change the slicing in this loop
Line 167 in 1d7811f
- use the swapped prediction only for the unlab samples
Line 179 in 1d7811f
- here add cross-entropy on the labeled samples, something like
F.cross_entropy(logits_lab, targets_lab)
Line 189 in 1d7811f
Something like this. It should not be too hard. Remember that the repo now contains code for UNO v2 that performs much better than the original version, so results are gonna be different.
from uno.
what's the main difference between v1 and v2? I note that you fix cross_entropy loss.
And I also have another problem? do you think multiple heads(unlabel heads) help a lot for the performance?
from uno.
Thank you so much for the fast reply! I will implement it following your guides
from uno.
The main difference is in the augmentations. I recommend you use the new version. With UNO v2 multiple heads do not help as much as before, so if you want to speed up computation you can decrease the number of heads.
from uno.
Hi Enrico,
The main difference is in the augmentations.
But, I find that both transforms.py
are identical in master and v2 branch. Had the new changes been ported to both the branches alike?
Kindly clarify when you are free. Thanks in advance!
~ Joseph
from uno.
Great! Thanks!
from uno.
Related Issues (14)
- License HOT 2
- How long does ImageNet experiments take? HOT 2
- Clarification question on num_large_crops HOT 2
- UNO_V2 results HOT 1
- The results on CIFAR10 HOT 2
- Issues with saving and loading checkpoints when using multiple gpus.
- a lot of questions about how to reproduce and cite the experimental results HOT 6
- Reproducing the paper results HOT 7
- Save inference images HOT 2
- swapped_prediction computation HOT 9
- Apply to a custom dataset HOT 2
- A question about the Eq.4 HOT 2
- loss_per_head seems wrong HOT 2
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 uno.