Comments (4)
Your observation is right. The operation of the gradient of FPGM is different from that of SFP.
For FPGM, the gradients of the pruned filters are zero, and for SFP, they are non-zero, refer to this link.
Several reasons for this:
-
The nonzero gradient of SFP would enlarge the model capacity, which is the main point of SFP. But the contribution of FPGM is about the filter selection criterion, so we would like the eliminate the effect of model capacity to compare fairly.
-
This kind of operation is also different from HFP (Please refer to HFP in my IJCAI paper). Although the selected filters are pruned and kept as zero, the connections of them remain.
Imagine the first case, we use 500 neurons to learn a training set for one epoch (This is HFP).
In the second case, we use 1000 neurons to learn and delete 500 of them. For every epoch, 500 neurons are different (This is SFP).
The third case, we use 1000 neurons to learn and delete 500 of them. For every epoch, 500 neurons are the same (This is something between SFP and HFP).
from filter-pruning-geometric-median.
Got it! Thank you~
from filter-pruning-geometric-median.
@he-y What if only change the filter selection method and make the selected filters different for every epoch?In other words, maintaining the advantages of both the model capability enlarge of SFP and the filter selection of FPGM?
from filter-pruning-geometric-median.
@he-y What if only change the filter selection method and make the selected filters different for every epoch?In other words, maintaining the advantages of both the model capability enlarge of SFP and the filter selection of FPGM?
I think the performance would be slightly better.
As discussed above, the original FPGM is "FPGM + half SFP". So the improvement of "FPGM + SFP" over "FPGM + half SFP" may be less than that of "SFP" over "HFP".
from filter-pruning-geometric-median.
Related Issues (20)
- Pruning result on ResNet-18 of Imagenet HOT 1
- Model size problem
- Question about baseline on ImageNet HOT 5
- Problems on the implementation HOT 1
- about training time HOT 4
- implementation on efficientnet HOT 2
- Experiment Question
- About function get_filter_similar() HOT 7
- Confusion with init_rate HOT 1
- Accuracy of pruned vgg without pruning
- Result of resnet18 on imagenet is low until epoch60
- 你好,有个代码段没理解 HOT 8
- TypeError: 'module' object is not callable HOT 2
- small model is not small HOT 6
- Can model compression be used for GAN?
- How to integrate FPGM and SFP
- 公布的模型参数怎么理解 HOT 1
- 作者提供的训练的模型,云盘下载之后,解压内部tar文件的时候显示资源有问题,解压失败 HOT 1
- 您好!请问get_small_model.py文件如何使用?谢谢! HOT 1
- FPGM on object detection model & implementation of NNI 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 filter-pruning-geometric-median.