mil-ad / snip Goto Github PK
View Code? Open in Web Editor NEWPytorch implementation of the paper "SNIP: Single-shot Network Pruning based on Connection Sensitivity" by Lee et al.
License: MIT License
Pytorch implementation of the paper "SNIP: Single-shot Network Pruning based on Connection Sensitivity" by Lee et al.
License: MIT License
Hi!
weights and its gradients are set to 0 in the code which i think is different from real pruning.
I noticed that you copy the model and reinitialize it to calculate the gradients in SNIP function by "nn.init.xavier_normal_(layer.weight)". Thus, the initialization used for pruning is not the exact model used for training. Am I right?
Hello, my research direction is neural network hardware accelerators. I need model parameters to test. Do you have well-trained models, such as vgg, LeNet, AlexNet, etc. Any network model is fine, I need more models to test, please send me an email, [email protected], thank you very much.
Line 36 in snip.py should be
layer.weight_mask.requires_grad = False
not as it is
layer.weight.requires_grad = False
which essentially ruins the entire model :P
Thank for you great work! will you release the code adjusting the snip to resnet?
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.