Comments (1)
Yes we tried with a ViT backbone! In short it worked out-of-the-box with the following setup (similar to DINO):
- model: ViT-S/16
- batch-size: 1024
- support-set: 6720 (960 classes, 7 imgs/class)
- temperature: 0.1
- sharpening: 0.25
- me-max regularization: true
- starting LR: 2.0e-4
- LR: 1.0e-3
- final LR: 1.0e-6
- start WD: 0.04
- final WD*: 0.4
- projection head (same as RN50, but with GELU activations and the following dimensions): [256, 256, 256]
- prediction head (same as RN50, but with GELU activations and the following dimensions): [256, 256]
- optimizer: AdamW
Evaluation: soft NN 10% labels (no fine-tuning):
- 100 epochs of pre-training: 70.9% top-1 on IN1k
- 300 epochs of pre-training: 72.3% top-1 on IN1k
*Although you can probably just use a constant WD value, i'm not sure the increasing schedule was that important in this experiment.
Let me know if there's some other information about the setup you need that I forgot to mention!
from suncet.
Related Issues (20)
- difference between suncet loss and supervised contrastive loss HOT 3
- Using pretrained networks and small amounts of labelled data HOT 5
- why the label are all some when training? HOT 3
- Negative loss HOT 1
- `ClassStratifiedSampler` HOT 1
- "training" parameter missing from "meta" section of config file cifar10_snn.yaml HOT 5
- Installation issue (apex) HOT 4
- Question for ClassStratifiedSampler HOT 3
- High memory usage even with low batch size and support set size HOT 10
- Mismatch in metrics for UDA method HOT 2
- running fine tuning on a custom dataset HOT 3
- Do you have any slides or video for this paper HOT 2
- Requirement to run Single-GPU training HOT 1
- [Question] Using h as the target vector HOT 3
- Error with udata loader HOT 1
- adjusting code to fit a multi-label problem HOT 7
- error when loading the optimizer's state dict HOT 11
- About Result Validation for Custom Datasets
- Strange Result Validation for Custom Datasets
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 suncet.