GithubHelp home page GithubHelp logo

Comments (5)

FelixCaae avatar FelixCaae commented on June 12, 2024

我也遇到了同样的情况

from mobilenetv3-ssd.

chengyequn avatar chengyequn commented on June 12, 2024

请问你在voc上的mAP是多少呀

from mobilenetv3-ssd.

xialei1020 avatar xialei1020 commented on June 12, 2024

请问你们是如何修改数据写入的

from mobilenetv3-ssd.

shaoshengsong avatar shaoshengsong commented on June 12, 2024

https://github.com/shaoshengsong/MobileNetV3-SSD-Compact-Version

from mobilenetv3-ssd.

JF-Lee avatar JF-Lee commented on June 12, 2024

11.19更新:
训练集:VOC07+12,测试集:VOC07-test,
使用SGDR学习率调整策略,初始学习率为0.01,学习率调整周期为100个epoches,总共训练610个epoches,
预训练模型:mb3-ssd-lite-Epoch-149-Loss-5.782852862012213.pth,
batch_size:32,
能得到的最好的Loss是4.07,请问怎样进一步调整学习策略?
原提问:
你好,当我使用您提供的PASCAL的预训练模型(mb3-ssd-lite-Epoch-149-Loss-5.782852862012213.pth)对几张图片进行检测时,每张图片都检测不到任何一个物体。
然后,我在上述检查点的基础上进行finetune,使用VOC2007+VOC2012数据集训练了100个epoch,batch_size=32,lr=0.0005+multistep([40,80,]),使用新训练的模型再次检测,部分图片能检测到物体,但是准确度还是比较低。
对此,我有两个问题想请教您:

您在使用上述PASCAL模型进行检测时效果如何?是我操作不当还是模型本身专准确度就不高?
如果想进一步提高准确度,我需要如何训练?比如是否应该加大数据集或改进训练参数。

请问一下你在VOC训练一个epoch大概要多久?

from mobilenetv3-ssd.

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.