search

carrierlxk / COSNet

See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks (CVPR19)
320 stars 62 forks source link

不能找到utils.colorize_mask和data.DataLoader #3

Closed HuangLian126 closed 4 years ago

HuangLian126 commented 5 years ago

您好！拜读了您的文章 See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks，非常棒的无监督解决方案。我准备测试您的代码，十分遗憾无法跑通，缺少utils.colorize_mask和data.DataLoader。您可以上传相关的代码吗？万分感谢！！！

carrierlxk commented 5 years ago

你好， utils.colorize_mask可以屏蔽掉，另外一个是将test_coattention_conf.py第11行去掉屏蔽。我已经更新了test_coattention_conf.py这个函数。

HuangLian126 commented 5 years ago

非常感谢能收到您的回复，我重新测试一下

---原始邮件--- 发件人: "Lu Xiankai"<notifications@github.com> 发送时间: 2019年9月12日(星期四) 下午2:30 收件人: "carrierlxk/COSNet"<COSNet@noreply.github.com>; 抄送: "Author"<author@noreply.github.com>;"HuangLian126"<785105390@qq.com>; 主题: Re: [carrierlxk/COSNet] 不能找到utils.colorize_mask和data.DataLoader (#3)

你好， utils.colorize_mask可以屏蔽掉，另外一个是将test_coattention_conf.py第11行去掉屏蔽。我已经更新了test_coattention_conf.py这个函数。

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.

HuangLian126 commented 5 years ago

打扰了，遇到一个新问题。照着您的回复，删除与davis无关的东西之后，运行依然报错"PyTorch splits its backend into two shared libraries: a CPU library and a CUDA library; this error has occurred because you are trying to use some CUDA functionality, but the CUDA library has not been loaded by the dynamic linker for some reason". 我用的pytorch1.2.0，上述问题是版本问题还是？

------------------ 原始邮件 ------------------ 发件人: "gewenbin292"<notifications@github.com>; 发送时间: 2019年9月12日(星期四) 下午2:51 收件人: "carrierlxk/COSNet"<COSNet@noreply.github.com>; 抄送: "老黄"<785105390@qq.com>;"Author"<author@noreply.github.com>; 主题: Re: [carrierlxk/COSNet] 不能找到utils.colorize_mask和data.DataLoader (#3)

还会提示5个错误，须将与davis无关的删掉，好像只提供了davis测试

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.

carrierlxk commented 5 years ago

应该是版本的问题，或者你直接用cpu跑吧

shoutOutYangJie commented 5 years ago

应该是版本的问题，或者你直接用cpu跑吧 looking forward to your training code .