Giter Site home page Giter Site logo

pytorch-diou-yolov3's Introduction

简体中文 | English

miemie2013

个人介绍

好康的照骗比枯燥乏味的文字更具有说服力↓

Example 0

Example 0

Example 0

友情链接

  • miemieGAN miemieGAN是咩酱个人开发与维护的图像生成库,以咩酱的名字命名,实现了stylegan2ada等算法,目前文档完善中,欢迎大家试玩。

传送门

算法1群:645796480(人已满)

算法2群:894642886

粉丝群:704991252

关于仓库的疑问尽量在Issues上提,避免重复解答。

B站不定时女装: _糖蜜

知乎不定时谢邀、写文章: 咩咩2013

西瓜视频: 咩咩2013

微信:wer186259

本人微信公众号:miemie_2013

技术博客:https://blog.csdn.net/qq_27311165

AIStudio主页:asasasaaawws

欢迎在GitHub或上面的平台关注我(求粉)~

打赏

如果你觉得我的仓库对你很有帮助,可以给我打钱↓

Example 0

咩酱爱你哟!

pytorch-diou-yolov3's People

Contributors

miemie2013 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

pytorch-diou-yolov3's Issues

pattern训练问题

对之前训练好的模型epoch74,继续训练,该怎么弄?
image
用经过1_lambda2model.py之后的模型训练吗

求部分文件

大佬,缺少requirement.txt和demo_video.py希望能上传一下嘛??

训练其中几类目标

请问,如何使用coco数据集训练其中几类目标,数据集和标签可以写脚本制作,网络参数部分,不知大佬可否提点建议。

今天用gpu训练突然发现一个问题

用gpu训练时,将学习率降维10-5,训练了几个epoch后loss就变为nan,但是用cpu训练却没问题。而且gpu无论怎么改变learning rate都不起作用

感谢

第一次看见这么人性化的讲解 爱了

loss nan

您好,我只训练一个类别时,训练几个epoch后,就出现了loss nan的情况,减小学习率也不行

发现是这3根loss中有的数据为nan,
ciou_loss = ciou_loss.sum((1, 2, 3, 4)).mean() # 每个样本单独计算自己的ciou_loss,再求平均值
conf_loss = conf_loss.sum((1, 2, 3, 4)).mean() # 每个样本单独计算自己的conf_loss,再求平均值
prob_loss = prob_loss.sum((1, 2, 3, 4)).mean() # 每个样本单独计算自己的prob_loss,再求平均值

我把数据加1e-8也不行
pos_loss = respond_bbox * (0 - T.log(pred_conf+1e-8))
neg_loss = respond_bgd * (0 - T.log(1 - pred_conf+1e-8))

后来:我把为nan的数据过滤掉,结果loss全部为0了

ciou_loss = ciou_loss[(ciou_loss != ciou_loss) == False].sum() # 每个样本单独计算自己的ciou_loss,再求平均值
conf_loss = conf_loss[(conf_loss != conf_loss) == False].sum() # 每个样本单独计算自己的conf_loss,再求平均值
prob_loss = prob_loss[(prob_loss != prob_loss) == False].sum() # 每个样本单独计算自己的prob_loss,再求平均值
请问一下,这个有办法吗?

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.