-
-
Notifications
You must be signed in to change notification settings - Fork 107
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Negative mining 以及 triplet loss #12
Comments
你好,主要在paddle那边。我们最后混合了多个模型,一部分模型用了 negative mining @miraclebiu mingyue,你可以给个行号么,,辛苦,, |
您好,郑博士.能否补充这篇论文中有关三元组相关代码. |
triplet loss可以参考 https://github.com/douzi0248/Re-ID/blob/master/train_11.py#L182 DG-Net只是个option, 我们最后只是一部分模型用了,但是没有直接用DGNet训的reid 模型,因为生成部分显存占用比较大,不能上一些大网络比如EF5 或者SENet,或者大resolution。 当时只是用ResNet-50 去训练生成,然后把生成的图片当作额外的ID 来训练。 可以参考https://github.com/NVlabs/DG-Net 基本改一下路径和输入大小(行人是256128,车是256256)就可以跑起来。 |
谢谢 |
你好,难样本挖掘这块,我看论文没看懂,可以详细说一下吗 |
郑博士您好!
您在论文中提到有minibatch中50%的图片用作Negative mining ,并且使用了度量学习的方法.请问Negative mining 以及 triplet loss对应于代码中的何处?
The text was updated successfully, but these errors were encountered: