Comments (3)
@impredicative At the start time of this project Python 3.6 was the latest version. I think Python 3.6 is still a more popular release of Python today. The authors are more familiar with PyTorch 0.3.x. Some of the code we used is also written in Pytorch 0.3.x.
What affects the results is the hyperparameters rather than versions. We don't have to rewrite and rerun all the resource-consuming experiments when a new release comes out. The code can be adapted to any version of Python or PyTorch straightforwardly while still able to reproduce the results. Though I think there's no need to do this, as you can install virtual environment instead.
from rethinking-network-pruning.
The Python version we use in our experiments is 3.6.4. The package torch version is 0.3.1.
from rethinking-network-pruning.
Why not ensure the results are reproducable with the current versions of Python and Pytorch, at least as of the release date of the paper? It's a reasonable expectation. Pytorch 0.4.1 has been out since July 2018. The paper is dated Oct 2018.
from rethinking-network-pruning.
Related Issues (20)
- Pruning strategy HOT 1
- 关于阻止已经置零的通道进行权重更新出现的问题 HOT 2
- size mismatch, m1: [2 x 288], m2: [8 x 120] HOT 1
- after network-slimming,the size of modell are the same as premodel? HOT 4
- count_flops HOT 2
- Question for Network Slimming on cifar 100 HOT 2
- IndexError: index 0 is out of bounds for dimension 0 with size 0 HOT 3
- when should I train it? HOT 4
- Question about predefined structured pruning HOT 1
- A question about the training epochs HOT 2
- Network slimming loss function HOT 2
- Cifar10 vgg19 zero remaining channel (network slimming) HOT 6
- updateBN HOT 1
- Some questions about ThiNet HOT 2
- Reproduce Fig. 4 from paper HOT 1
- VGG-16 on CIFAR10 dataset architecture
- What is 'PATH TO THE MODEL' HOT 1
- VGG-16 and ResNet-50 from Pytorch Model Zoo Not found HOT 2
- Error while running l1-norm-pruning on Windows machine HOT 3
- Pretrained model for [imagenet] [slimming] not working HOT 2
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 rethinking-network-pruning.