drsleep / nas-segm-pytorch Goto Github PK
View Code? Open in Web Editor NEWCode for Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells, CVPR '19
License: Other
nas-segm-pytorch's People
Contributors
Stargazers
Watchers
Forkers
yangsenwxy xiaofengqing kepengxu babygothacked jonathanfly ddeeppnneett kapitsa2811 munian-ustc aihill peterzhousz terryyida blyucs wh-forker zechendev adelaide-ai-group waterbearbee sailfish009 killsking frodab 7u5 weichenrs pinglmlcv paul-ang ephisennas-segm-pytorch's Issues
Optimize the search for inferencing
@DrSleep Thank you for your hard work,
My goal is to search for an architecture that balance accuracy and high inferencing speed on cpu.
- Is there an option to limit the search space to not exceed a certain limit of
parametersflopsadds? - How to inference an image using cpu only?
zero reward?
Thanks for the open code!
When performing the search procedure, i always got zero reward after epoch 69. Is it normal?
reward: 0.6049, epoch: 69, params: 2152613, epoch_time: 27.7015, genotype: [[3, [1, 0, 9, 9], [4, 1, 7, 1], [0, 7, 10, 5]], [[3, 3], [4, 4], [3, 3]]]
reward: 0.0000, epoch: 70, params: 2277317, epoch_time: 7.8641, genotype: [[6, [0, 1, 3, 1], [0, 4, 0, 10], [2, 2, 6, 10]], [[1, 0], [2, 3], [2, 0]]]
reward: 0.0000, epoch: 71, params: 2088101, epoch_time: 7.4487, genotype: [[0, [0, 1, 7, 1], [4, 1, 4, 3], [5, 2, 7, 7]], [[3, 1], [4, 2], [2, 5]]]
reward: 0.0000, epoch: 72, params: 2147717, epoch_time: 7.7244, genotype: [[9, [1, 0, 6, 10], [3, 0, 2, 4], [4, 2, 1, 10]], [[1, 3], [0, 3], [2, 3]]]
Searching on an 8GB GPU
What configurations should be made in-order to search and train on a single 8gb gpu
PASCAL VOC segmentation dataset expanded with annotations from BSD
Could you provide the download link
Open source the whole training processing
could you please open source the whole training process? I think that will be more valuable than this fixed model. Thank you for your time.
Official models trained on CityScapes
Hi Vladimir, could you please provide official segmentation models trained on CityScapes?
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.