Comments (3)
Hello,
Yes, shape adaptor networks as similar to other standard network designs can be trained with multi-GPUs. Our ImageNet results were trained with 8 GPUs. However, considering that many number of training images, we need to re-search the hyper-parameters. You could start using hyper-parameters listed for ImageNet as a start (see Arxiv-version paper Appendix).
Sk.
from shape-adaptor.
Hello,
Yes, shape adaptor networks as similar to other standard network designs can be trained with multi-GPUs. Our ImageNet results were trained with 8 GPUs. However, considering that many number of training images, we need to re-search the hyper-parameters. You could start using hyper-parameters listed for ImageNet as a start (see Arxiv-version paper Appendix).
Sk.
Could you please tell me how to set multi-gpus?The parameter gpu in model_training.py is of type int instead of array.
thx!
from shape-adaptor.
I would suggest following the official ImageNet training guide. https://github.com/pytorch/examples/tree/master/imagenet
from shape-adaptor.
Related Issues (8)
- ShapeAdaptor issue HOT 4
- some problems about experiments HOT 8
- I wonder if it can be use in other data format like nlp data HOT 1
- resnet shape-adaptor HOT 5
- Question about reimplementation HOT 9
- Question about default weight decay in model_training_imagenet.py HOT 1
- GMACs for ImageNet dataset? HOT 1
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 shape-adaptor.