sjmikler / snip-pruning Goto Github PK
View Code? Open in Web Editor NEWReproduction and analysis of SNIP paper
Reproduction and analysis of SNIP paper
Hello,
Thanks for implementing in PyTorch, but i believe there is a something wrong in the code.
In the original paper and implementation, loss is differentiated against the connection indicators and not the weights.
From Lee's original code in line 67:
grads = tf.gradients(loss, [mask_init[k] for k in prn_keys])
I understand you have weight = indicator * weight
before computing gradients, but i can't see where you extract the gradients for the indicators only. I see you've posted on the pytorch forum about this but nobody has answered properly.
Hi,
Thanks for sharing your implementation ! I like how the weight is pruned via the method in the Prune class. However, I notice that during the training phase, your code call op() to zero out the pruned weight. But this is not done in NN.evaluation and NN.predict. I think this would cause the output accuracy to be misleading since the data is forward through a pruned network with one extra optimization step. (i.e. Weights that are supposed to be zero would no longer be zero due to the gradient update)
Thanks for any further clarification !
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.