forked from Eric-mingjie/rethinking-network-pruning
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
32e4186
commit 5e8c5ae
Showing
1 changed file
with
4 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,12 +1,14 @@ | ||
# CIFAR Experiments | ||
This directory contains all the CIFAR experiments in the paper, where there are three pruning methods in total: | ||
This directory contains all the CIFAR experiments in the paper, where there are four pruning methods in total: | ||
|
||
1. [L1-norm based channel pruning](https://arxiv.org/abs/1608.08710) | ||
2. [Network Slimming](https://arxiv.org/abs/1708.06519) | ||
3. [Soft filter pruning](https://www.ijcai.org/proceedings/2018/0309.pdf) | ||
4. [Non-structured weight-level pruning](https://arxiv.org/abs/1506.02626) | ||
|
||
For each method, we give example commands for baseline training, finetuning, scratch-E training and scratch-B training. | ||
For each method, we give example commands for baseline training, finetuning, scratch-E training and scratch-B training. | ||
|
||
We also give our implementation for [Lottery Ticket Hypothesis](https://arxiv.org/abs/1803.03635). | ||
|
||
## Implementation | ||
Our code is based on [network-slimming](https://github.com/Eric-mingjie/network-slimming) and [pytorch-classification](https://github.com/bearpaw/pytorch-classification). |