Comments (7)
Hi @brewormly, yes the current checkpoints only include the "target_encoder" since those are the network used at the end of pre-training to obtain the results in the paper, but I would be happy to release the full checkpoints as well in case you find these useful! Will ping you once these are online!
from msn.
I have also some issues regarding the pre-trained checkpoints. The checkpoints only include the keys "target_encoder" and "prototypes". If I want to load the checkpoint via the training script, I get errors because the keys "epoch" and "encoder" are missing.
from msn.
@MidoAssran possible to release the ImageNet-1k specific checkpoints (fine-tuned and / or linear-eval'd)?
By "linear-eval'd" I mean keeping the target encoder frozen and just training a linear layer on top of it. So, essentially, the target encoder params (which are already released) and the linear layer params.
from msn.
Also, the target_encoder
key in the released weights -- seems like it contains two things - the actual encoder plus the projection head (module.fc*
params). Is the projection head needed for downstream tasks?
from msn.
Hi @BestSonny, There are 1024 prototypes used in the loss, but I just checked the ViT-B/16 and ViT-B/4 pre-trained weights, and they both have the correct output dimension of 768. Please let me know if you would like some more clarification or help loading the models!
from msn.
I have also some issues regarding the pre-trained checkpoints. The checkpoints only include the keys "target_encoder" and "prototypes". If I want to load the checkpoint via the training script, I get errors because the keys "epoch" and "encoder" are missing.
I have the same issue !
from msn.
Hi @brewormly, yes the current checkpoints only include the "target_encoder" since those are the network used at the end of pre-training to obtain the results in the paper, but I would be happy to release the full checkpoints as well in case you find these useful! Will ping you once these are online!
Sorry for the late reply after one year. I wonder if there is still a plan to release the full checkpoints? I think they will be very helpful in continuing the training for other tasks.
from msn.
Related Issues (20)
- can help add vit-small-8 and vit-base-4 config file? HOT 1
- linear_eval.py #L327 HOT 1
- Could you please give the version of cyanure you used? HOT 1
- About the 1% In1k semi-sup evaluation HOT 1
- module 'cyanure' has no attribute 'preprocess' HOT 4
- The detail setting for 1% evaluation HOT 1
- Include full checkpoint HOT 1
- Custom dataset Linear Eval
- Lambda for logistic regression evaluation
- Performance when small batch size
- why did not take block-wise mask strategy? HOT 1
- vit-b-16 config
- can you release the time complexity of training ViT B/4 and ViT L/7
- Using just the encoder
- How to change MSN loss to PMSN loss? (from paper "The Hidden Uniform Cluster Prior in Self-Supervised Learning") HOT 1
- What is the use of "AllReduce"?
- The loss has converged at early stage?
- No such file HOT 1
- Duplicate GPU detected error HOT 4
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 msn.