Comments (4)
Hi,
We are working on preparing the release for the distillation part in https://github.com/fmassa/deit/tree/distillation, and we will be opening a PR once we finish validating that the refactored code works, which should be later this week.
from deit.
Hi,
We are working on preparing the release for the distillation part in https://github.com/fmassa/deit/tree/distillation, and we will be opening a PR once we finish validating that the refactored code works, which should be later this week.
Thanks for your great work! By the way, can you share us fine-tuing code? I tried 384 for pretrained model and cannot work!
Others need this too! link
from deit.
Hi,
Code for distillation has been merged into master, and the code for finetuning is in #43 and will be merged soon. Once they are merged I'll upload the weights for the pre-trained models.
from deit.
Hi,
We've merged the code for distillation and finetuning in #42 and #43, and added the pre-trained weights in #50.
Given that those are now available, I'm closing this issue but let us know if you have any further questions
from deit.
Related Issues (20)
- What is the ImageNet-1K Top-1 accuracy of Training from 0 to 400 epochs (Fig. 5 of Deit III paper)
- Are the hyperparameters for DeiT-T and for DeiT-S any different than DeiT-B? HOT 1
- What's the accuracy of deit-S without pre-trained on CIFAR10 HOT 1
- Does the EMA is used in DeiT-III? HOT 3
- Multinode Slurm Training
- What batch size number other than 1024 have been tried when training a DeiT model?
- Can I use timm==0.4.12 instead of timm==0.3.2 ? HOT 1
- Meaning of the model name ( ResMLP) HOT 1
- Multi-node support
- how to implement document layout analysis use Deit-B HOT 2
- unexpected keyword argument 'pretrained_cfg' HOT 2
- Single machine multi-GPU training
- What are the hyperparameters for DeiT-III (epoch 400 or 600)?
- The ablation experiment of DeiT HOT 2
- how to implement cosub training use deit-III
- how to implement cosub training use deit-III HOT 2
- DeiT depth 24 (CaiT - TABLE 1) HOT 2
- ImageNet21K data preparation for pre-training HOT 5
- batch_size flag HOT 2
- Code for cosub
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 deit.