d-x-y / awesome-autodl Goto Github PK
View Code? Open in Web Editor NEWAutomated Deep Learning: Neural Architecture Search Is Not the End (a curated list of AutoDL resources and an in-depth analysis)
License: MIT License
Automated Deep Learning: Neural Architecture Search Is Not the End (a curated list of AutoDL resources and an in-depth analysis)
License: MIT License
Hi,
I'm new to NAS. And I want to know the difference between type β-β and type βOtherβ.
Thank you!
Hello,
Here is the link to our ICLR 2019 paper on automatically searching for a compressed architecture with Bayesian optimization: https://openreview.net/forum?id=S1xLN3C9YX . Our code is also available here: https://github.com/Friedrich1006/ESNAC .
Our lab also has a ICLR 2018 paper (https://openreview.net/forum?id=B1hcZZ-AW) that uses reinforcement learning to search for compressed architectures.
Would you please add them to the list? Thanks!
Towards modular and programmable architecture search
Paper: https://arxiv.org/abs/1909.13404
Code: https://github.com/negrinho/deep_architect
Thank you
Hi,
Here is our new ICCV paper "AutoGAN: Neural Architecture Search for Generative Adversarial Networks"
Paper Link: https://arxiv.org/pdf/1908.03835.pdf
code link: https://github.com/TAMU-VITA/AutoGAN
Thanks!
Hi, our new paper about nas has accepted by CVPR2019, would you please add it on your list?
Name:
Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
Link:
https://arxiv.org/abs/1903.03777
Dear D-X-Y,
We have one ICCV 2021 paper about zero-shot Neural Architecture Search:
paper arXiv link: https://arxiv.org/abs/2102.01063
Github: https://github.com/idstcv/ZenNAS
It would so nice of you if you could kindly append this work to the paper list. Thank you very much!
Poster: https://cms.tinyml.org/wp-content/uploads/talks2022/Saha-S.-Sayan-SW-tools.pdf
Code: https://github.com/ARM-software/mango/tree/master/examples/THIN-Bayes
We developed a new state-of-art Bayesian NAS framework. We would be happy if you add it to your list.
There are over 30 citations of this survey.
@article{he2019automl,
title={AutoML: A Survey of the State-of-the-Art},
author={He, Xin and Zhao, Kaiyong and Chu, Xiaowen},
journal={arXiv preprint arXiv:1908.00709},
year={2019}
}
Hi Xuanyi,
Thanks for making this awesome summary list!
Here is our new CVPR 2020 paper "Binarizing MobileNet via Evolution-based Searching"
Paper Link: https://arxiv.org/abs/2005.06305
Type is Evolution Algorithm.
Thanks!
The Library PyGlove only have a neuralPS paper, not an usable Library, where is the code?
Hi Xuanyi,
Thanks for the awesome paper list for NAS!
Here is our CVPR 2020 paper about NAS based on performance prediction.
Paper Title: A Semi-Supervised Assessor of Neural Architectures
Paper link: https://openaccess.thecvf.com/content_CVPR_2020/papers/Tang_A_Semi-Supervised_Assessor_of_Neural_Architectures_CVPR_2020_paper.pdf
Thanks!
I am beginner in DL,i know the basic running models on dataset and getting results but somehow i got assigned to work on using Fixres strategy.Can u provide me some help that how to run this ??am clueless
Hi,
Here is our new CVPR 2020 paper "AdversarialNAS: Adversarial Neural Architecture Search for GANs"
Paper Link: https://arxiv.org/pdf/1912.02037.pdf
Code link: https://github.com/chengaopro/AdversarialNAS
Type is gradient-based.
Thx!
Hi Xuanyi,
We have a NAS related paper in ICLR 2020, 'Fast Neural Network Adaptation via Parameter Remapping and Architecture Search'.
Paper: https://openreview.net/forum?id=rklTmyBKPH
Code: https://github.com/JaminFong/FNA
We wonder if it is OK to add this paper. Thank you!
paper: https://openreview.net/forum?id=BylQSxHFwr
code: https://github.com/meijieru/AtomNAS
Thanks.
Hi,
Would you please add our recent paper on NAS to the list? The title is Neural Architecture Optimization , which is accepted at NIPS this year. Maybe it can be categorized into the gradient based method. Thanks.
Best
A declarative, efficient, and flexible JavaScript library for building user interfaces.
π Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. πππ
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google β€οΈ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.