manuscrit / selectivebackpropagation Goto Github PK
View Code? Open in Web Editor NEWImplementation of the paper: Selective_Backpropagation from paper Accelerating Deep Learning by Focusing on the Biggest Losers
Implementation of the paper: Selective_Backpropagation from paper Accelerating Deep Learning by Focusing on the Biggest Losers
When self.update_weights_func(effective_batch_loss)
, should we do like this?
`
self.optimizer.zero_grad()
self.update_weights_func(effective_batch_loss)
self.optimizer.step()
`
Could you provide a demo script using SelectiveBackPropagation and/or provide a docstring for the __init__
method? Thanks!
Hello
When I run the code, I got the following error
self.loss_hist.extend(cpu_losses.tolist())
TypeError: 'float' object is not iterable
in the function :
def selective_back_propagation
Please help to correct it
Many 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.