1e100 / mnasnet_trainer Goto Github PK
View Code? Open in Web Editor NEWPyTorch 1.1.0 training setup for MNASNet that will get you close to "paper" numbers.
License: GNU General Public License v3.0
PyTorch 1.1.0 training setup for MNASNet that will get you close to "paper" numbers.
License: GNU General Public License v3.0
thanks for your great job.
please tell me , Is the model with SE module?
Dear @1e100 ,
Nice work!
According to my experience, training mnasnet will takes about 7~8G GPU memory for batch_size=96(mobilenetV2 setting), since i tried to reproduce paper values with pytorch 0.4 months ago.
Are you sure that you could use batch_size=740 for mnasnet1.0 with only 4 1080Ti?
Would you please share batch size setting to reproduce paper value? since it is never mentioned and part of the training paras were changed compare to paper v1.
Thanks very much for your help!
hi, 1e100
Have u tried implemented the mnas searching part?
Thanks
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.