Comments (1)
Hi
1e-2
is the recommended value for ImageNet classification task.
In general, we recommend using a weight decay value equal to baseline optimizer (AdamW).
You can directly use hyper parameters of AdamW to AdamP.
If you don't have any hyper parameter values for AdamW, weight decay 0 is good for the first try.
Because many tasks use zero weight decay, so just try this and slowly increase the weight decay for tuning.
from adamp.
Related Issues (13)
- Hyperparameters of AdamW HOT 7
- example params HOT 2
- unexptected behavior of AdamP on CPU? HOT 5
- Could it be equivalent to normalize the weights ? HOT 2
- Good bug in your implementation of AdamP HOT 1
- learning rate scheduler for adamp? HOT 3
- The difference with Adam and AdamP in the code HOT 3
- Experiment of Adam with warm up? HOT 2
- Question about eq (5) in section 2.3 HOT 1
- Depereciation warning in pytorch 1.5 (maybe and above?) HOT 4
- Builtin cosine_similarity HOT 4
- Runtime: Adam vs AdamP 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 adamp.