Comments (1)
Indeed tensorflow model_optimization library is slightly different and not as transparent. Pruning Wrapper always applies the mask to the weights here. If I remember correctly we prune the gradients on mnist experiments, too (see here).
So the results should be same.
Validation set in mnist experiments are created from the training set itself (see here). I don't think it would make much difference to use a different batch each time, but I think for simplicity it make sense to use the current batch. I think the reasoning for fixing this batch was to enable using a potentially larger batch size for updating masks.
Again I recommend using tf1 code for larger experiments.
from rigl.
Related Issues (13)
- No module named 'officialresnet' HOT 2
- RigL TF2 - Initial Sparsification HOT 3
- RigL TF2 on Resnet50 + Imagenet HOT 1
- Using Rigl to train with structured sparsity HOT 1
- Hello, can I use this method to sparse my own neural network? HOT 3
- Question: what is the speed up gain from Rigl and other methods implemented here in training? HOT 1
- Specify TF and TF.data versions? HOT 2
- Grow & Drop Ambiguity HOT 6
- How to train own convolutional network HOT 2
- How to load pretained weights? HOT 1
- Can you post the CIFAR-10 results of the paper? HOT 1
- MetaInit w. VGG HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rigl.