Sorrry，do you hava python3 and tensorflow version? i don't know caffe, if you hava that version,please give me,thank you
xiaolongxia520 opened this issue · comments
Unfortunately this project was developed before the birth of tensorflow and
pytorch, thus we didn't plan to develop our algorithm using the two tools.
Currently we do not have an official implementation based on tensorflow and
pytorch.
At this moment, I would suggest that you could take a look at a few
third-party re-implementations of our work as below. Though most of them
are the re-implementation of our workshop version paper, the performance is
already very similar to that of our journal version.
https://github.com/flyingpot/pytorch_deephash
https://github.com/dingmyu/Pytorch-Image-Retrieval
https://github.com/xiaowangdu/cvprw15-win
…On Tue, Oct 27, 2020 at 5:02 AM xiaolongxia520 ***@***.***> wrote:
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#31>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/ACMC2MGPAIDWQNW4DV52F3LSM2ZHFANCNFSM4TAXFONQ>
.
不幸的是，这个项目是在tensorflow和pytorch诞生之前开发的，因此我们不打算使用这两个工具来开发我们的算法。目前，我们还没有基于tensorflow和pytorch的正式实现。目前，我建议您可以看一下以下第三方对我们工作的重新实现。尽管大多数都是重新编写我们的研讨会版本论文，但其性能已经与我们的期刊版本非常相似。 https://github.com/flyingpot/pytorch_deephash https://github.com/dingmyu/Pytorch-Image-Retrieval https://github.com/xiaowangdu/cvprw15-win
…
2020年10月27日，星期二，凌晨5:02 xiaolongxia520 @.***>写道：—您收到此消息是因为您已订阅此线程。直接回复此电子邮件，在GitHub < ＃31 >上查看，或退订< https://github.com/notifications/unsubscribe-auth/ACMC2MGPAIDWQNW4DV52F3LSM2ZHFANCNFSM4TAXFONQ >。
thank you very much!!!
and i want to know how you dispose the dataset of SUN397?If I can, can I add your WeChat and QQ?