Comments (3)
Hi @amirhfarzaneh ,
It is an arbitrary choice, this scaling strategy is commonly used to train convents.
Best,
Hugo
from deit.
Hi @amirhfarzaneh ,
It is an arbitrary choice, this scaling strategy is commonly used to train convents.
Best,
Hugo
Great! thank you for the clarification.
from deit.
Hi, is the denominator really an arbitrary choice? Scaling learning rates are done to make sure the gradients are averaged correctly in DDP, right? So shouldn't args.batch_size * utils.get_world_size() > 1
? In other words, the denominator cannot be arbitrary.
I'm not 100% sure hence the question marks.
from deit.
Related Issues (20)
- 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
- How to launch a training of CAIT models ?
- TracerWarning
- Hi,Why can't I find deit_tiny_distilled_patch16_224 in hubconf
- Checkpoints of IN21K pretrained deit III
- ViT-B Training for DeiT HOT 2
- Slow Training HOT 2
- random.seed(seed) in line 205 is commented
- Inclusion of Transformers Need Registers
- Training
- Question about different seeds per gpu with DDP
- Gradient accumulation code
- Will you be releasing the accuracy of the official deit III framework trained tiny version on IN1k?
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.