Skip to content
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

BYOL的预训练中好像使用了gt_label? #134

Open
youqingxiaozhua opened this issue Nov 14, 2022 · 1 comment
Open

BYOL的预训练中好像使用了gt_label? #134

youqingxiaozhua opened this issue Nov 14, 2022 · 1 comment
Assignees

Comments

@youqingxiaozhua
Copy link

  • 在byol的config 中设置了 num_classes=1000:
    num_classes: 1000
  • 在model中设置了self.classifier = nn.Linear(embedding_dim, num_classes),并且forward中将classif_out和label一起传给了head

image

outputs = self.head(a1, b1, a2, b2, classif_out, label)

  • 在L2 Head中将对比loss和有监督的CE loss加在了一起返回

image

outputs["loss"] = outputs['rep_loss'] + outputs["class_loss"]

@jerrywgz
Copy link
Collaborator

jerrywgz commented Feb 5, 2024

问题是否还存在,建议使用mae 可以先转到 https://github.com/PaddlePaddle/PLSC/tree/master/task/ssl/mae 来使用

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants