- +增加游戏难度,选择更多分割的拼图
- -减小游戏难度,选择更少分割的拼图
- start 开始游戏
进入游戏之后选择相应的难度点击start开始游戏,之后拼图随机打乱,将拼图拼回元素就算胜利。最低4x4拼图,最高8x8拼图,默认4x4的拼图。
由于需要动态生成不同规格的拼图,使用了js来修改背景图片的位置和每一个div的left和top。此处可能算是入侵式代码,指教符合规格且不用去增添几十个类的方法
- 删除了liveroader在js中的代码
- 2015.11.22 完成v1.0
Semi-Supervised Video Salient Object Detection Using Pseudo-Labels, IEEE International Conference on Computer Vision (ICCV), 2019
Home Page: https://kinpzz.com/publication/iccv19_semi_vsod/
License: MIT License
Real-time Segmenting Human Portrait at Anywhere
Ruifeng Yuan, Yuhao Cheng♯
, Yiqiang Yan, Haiyan Liu
Lenovo Research
Buidling1, No.10 Courtyard Xibeiwang East Road, Beijing, China
I found it use RCRNet too?
but "Real-time Segmenting Human Portrait at Anywhere" has no github traning code
RuntimeError: CUDA call failed (correlation_forward_cuda at correlation_cuda.cc:82)
According to the readme.md, we changed the same configuration. When we run generate_pseudo_labels.py, the program appears above error, could you please help us to solve this problem?
您好
看论文里,你们使用了DAVIS(3455)+VOS(7650)+FBMS(720)总共11825的GT数据,然后在此基础上,每5张图片使用1个GT同时生成1个pseudo label(论文中1/5setting),也就是大概2365GT+2365pseudo label来训练模型。 而不是利用VOS和FBMS的稀疏标注,使用GT来给未标注的数据生成label。请问我这样理解对吗?
感谢您回复
您好,读了您的文章后,我有一个这样一个问题:您用fgplg生成的 pseudo label和存在的gt 合在一起训练RCRNet 效果会比全部使用 GT效果要好么?因为我发现生成的 pseudo label对应的图片实际上是有GT的。
前辈您好,我在复现您RCRNet的结果时,基本上没怎么改您的代码,用您训练好的伪标签生成器每5帧生成1帧伪标签,目前DAVIS和FBMS数据集上的性能都差不多,但是VOS 的 test 数据集的性能差了5-6个点。后来干脆不用伪标签,直接将伪标签生成器的frame_between_label_num设置为0,这样的话,相当于直接生成的是20%的真值。 我用这个训练,VOS test数据集的指标还是差了5-6个点。 但是用您提供的best_model直接跑inference,VOS的指标又是一样的。目前猜测是VOS文件配置问题?
DAVIS数据集配置:JPEGImages是帧间隔为1,伪标签文件夹里的标签(真值)帧间隔为5
FBMS数据集配置:JPEGImages是帧间隔不定,对应原始100%真值的图(一般间隔为20帧),伪标签文件夹里的标签(真值)帧间隔再 乘以 5
VOS数据集配置:JPEGImages是帧间隔为1,伪标签文件夹里的标签(真值)帧间隔为15 x 5 =75
我不太确定到底是哪里错了,能帮我对一下VOS数据集配置有问题吗
前辈您好,最近一直在看您的RCRNet,有两个不太理解的地方。第一是,您的伪标签生成器输入是7个通道,其中有相邻帧的真值,但是在测试集上跑的时候,我们不可能把测试集的真值输入到伪标签生成器啊?那么论文中的伪标签生成器在VOS的test数据集的性能是如何得到的呢(Table 4 )? 第二,为什么伪标签能起到作用呢?它相比于真值,感觉还是不够好。。我是否可以这样理解:伪标签的指导意义远比它的错误信息多,所以能对训练结果有帮助?
前辈你好,请问对于图像预训练模型的两个数据集,是如何划分测试集、交叉验证集以及训练集的?
Hello, may I ask you about how can I get the MSRA-B_id.txt?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.