Comments (3)
CanyonWind
commented on June 8, 2024
If you are looking for some quick examples, there is an option --reduced-dataset-scale in train_imagenet.py and you can set to 10 or 100 so that only 1/10 or 1/100 ImageNet training images will be trained (of course the performance is doomed).
If you plan to work on other popular datasets, I think you can modify the dataloader in train_imagenet.py very easily by using gluon.data.vision.xxx. An example can be found here, official documentation can be found here.
Any contribution and pull requests are welcomed. Please feel free to submit and I will merge them into the master branch if everything works okay.
from single-path-one-shot-nas-mxnet.
CanyonWind
commented on June 8, 2024
Issue is closed due to no further questions. Please feel free to reopen it when necessary.
from single-path-one-shot-nas-mxnet.
xuehui1991
commented on June 8, 2024
@CanyonWind Thank you. I already solve the problem.
from single-path-one-shot-nas-mxnet.
Related Issues (14)
- Official Review HOT 14
- Context switching causes multi GPU idling HOT 2
- the loss of supernet can't converge HOT 5
- supernet training with resource constrain HOT 2
- Supernet model weights HOT 1
- Supernet Training with Constraints
- Export ONNX model HOT 1
- Supernet training is too slow
- the loss of supernet doesn't seem to converge HOT 11
- supernet training HOT 15
- evolution search HOT 4
- Channel selection is disabled after resuming HOT 1
- Bug in random_channel_mask HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from single-path-one-shot-nas-mxnet.