Giter Club home page Giter Club logo

Comments (9)

talebolano avatar talebolano commented on July 18, 2024

是在稀疏化训练之后么,是否剪枝过多?

from yolov3-network-slimming.

lucheng07082221 avatar lucheng07082221 commented on July 18, 2024

@talebolano 稀疏化率用的是默认0.0001 ,剪枝比例用的默认0.3 模型用的yolov3,这里面应该有个处理过程,就是当出现剪枝后的通道数为0的时候应该取当前层最大的channel保留把

from yolov3-network-slimming.

talebolano avatar talebolano commented on July 18, 2024

是的,应该保留,我看你只有最后几层被剪掉了,其他层都没有变过,你是用了什么数据集,稀疏化水平如何?

from yolov3-network-slimming.

lucheng07082221 avatar lucheng07082221 commented on July 18, 2024

@talebolano 这个是我训练数据的稀疏化水平: 020%:0.793500,2040%:0.875185,4060%:1.030651,6080%:1.364402,80~100%:6.337093

from yolov3-network-slimming.

talebolano avatar talebolano commented on July 18, 2024

看原论文上是稀疏化到0.01之后去减的

from yolov3-network-slimming.

lucheng07082221 avatar lucheng07082221 commented on July 18, 2024

@talebolano 你有没有试过在有些数据集上训练yolov2,由于数据本身复杂性,利用L1正则去稀疏可能也不会带来太大的稀疏性,导致根本无法剪枝,即每一层的channel都是有用的?

from yolov3-network-slimming.

talebolano avatar talebolano commented on July 18, 2024

是的,这也是困扰我的问题,我尝试过替换惩罚项,换成kl散度,剃度截断还有ista,都不怎么work。你看过rethinking the value of network pruning那篇论文了么,像那篇论文所说,也许可以对稀疏化这个步骤换一种思路

from yolov3-network-slimming.

lucheng07082221 avatar lucheng07082221 commented on July 18, 2024

@talebolano 还没仔细研究,我觉得想要剪枝效果好,首先前提是网络容量相对数据集要充分大,作者用cifar10做测试是不对的,cifar10只要一个很小的网络就可以达到高的精度

from yolov3-network-slimming.

EtheneXiang avatar EtheneXiang commented on July 18, 2024

请问下,这和剪枝是怎么实现的,怎么丢弃的。我理解中的剪枝的实现方法,就是为权重施加一个相同大小的Mask, Mask中只有激活的地方才是1,其余全0。
可是,作者这个就是真真正正的剪枝,剪完之后,通道确实少了,模型确实变小了

from yolov3-network-slimming.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.