Comments (4)
Eric-mingjie
commented on May 27, 2024
1
residual layer有两个通道，一个通道有卷积和bn，另一个通道一般都是identity mapping,我说的主干道就是identity mapping这个通道。这样做之所以能保证主干道channel数不变，是因为我们保证了卷积通道的input 和output的channel数和原来保持一致，这样才能和identity 通道出来的output相同维度，从而相加。之所以这样实现就是主干道channel数不变的体现。建议可以仔细去看下resnet的结构。
from network-slimming.
Eric-mingjie
commented on May 27, 2024
这样是为了保证主干道的channel数不变，如果没有channel selection layer, 主干道的channel数没法保证一致。
from network-slimming.
YuQi9797
commented on May 27, 2024
如果没有channel selection layer，主干道channel数无法保证一致，主要是体现在哪里呢？
从reprune.py中，我只理解到，BN层后面若是channel selection layer，则它本身BN层没有进行裁剪，而是对对应的channel selection layer进行设置，需要保留的设为1，需裁剪的为0。相当于为0的没有进行反向传播学习，只有为1的保留下来。 但我不知道这样做，为什么能保证主干道的channel数不变，不知道具体体现在哪里？ 希望能帮忙解答，谢谢！ 期待您的回复。
…------------------ 原始邮件 ------------------
发件人: "Eric-mingjie"<[email protected]>;
发送时间: 2020年7月7日(星期二) 凌晨1:09
收件人: "Eric-mingjie/network-slimming"<[email protected]>;
抄送: "919664295"<[email protected]>; "Author"<[email protected]>;
主题: Re: [Eric-mingjie/network-slimming] 关于channel selection layer的问题请教 (#50)
这样是为了保证主干道的channel数不变，如果没有channel selection layer, 主干道的channel数没法保证一致。
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
from network-slimming.
YuQi9797
commented on May 27, 2024
好的，明白了！ 谢谢您的帮助！
…------------------ 原始邮件 ------------------
发件人: "Eric-mingjie"<[email protected]>;
发送时间: 2020年7月7日(星期二) 晚上11:44
收件人: "Eric-mingjie/network-slimming"<[email protected]>;
抄送: "919664295"<[email protected]>; "Author"<[email protected]>;
主题: Re: [Eric-mingjie/network-slimming] 关于channel selection layer的问题请教 (#50)
residual layer有两个通道，一个通道有卷积和bn，另一个通道一般都是identity mapping,我说的主干道就是identity mapping这个通道。这样做之所以能保证主干道channel数不变，是因为我们保证了卷积通道的input 和output的channel数和原来保持一致，这样才能和identity 通道出来的output想同维度，从而相加。之所以这样实现就是主干道channel数不变的体现。建议可以仔细去看下resnet的结构。
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
from network-slimming.
Related Issues (20)
- resnet50 HOT 1
- 为什么定义的resnet网络训练时gpu显存占用这么大啊？
- 为什么我裁剪完成后，模型运行占用的显存比没裁剪的还要高？ HOT 1
- 预测单张照片时，准确率只有0.0几 HOT 2
- Minor Bugs caused by old version
- Sparse Confusion HOT 1
- channel_selection layer intraining process HOT 2
- 剪枝后保存的权重文件和newmodel加载不上 HOT 3
- RuntimeError: Given groups=1, weight of size [15, 14, 1, 1], expected input[64, 16, 32, 32] to have 14 channels, but got 16 channels instead HOT 1
- If the remaining channel for a layer is zero, it reports zero division error HOT 2
- 原论文中的memory是指 HOT 6
- TypeError: item() takes no arguments (1 given) HOT 1
- mnn加载剪枝模型错误 HOT 1
- 经稀疏训练剪枝后模型变小，但是refine微调后模型又变大了
- 关于L1 regular HOT 1
- m.weight.grad.data.add_的问题
- 问题咨询：剪枝后通道数为0 HOT 7
- RuntimeError: CUDA error: device-side assert triggered HOT 1
- About other visions
- 题外话：模型压缩如何入门？对于自己的网络架构该如何着手去写剪枝代码？
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 network-slimming.