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.

Sign up for GitHub

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

Jump to bottom

Q-former #89

Open

CoderXuans opened this issue Oct 29, 2024 · 2 comments

CoderXuans commented Oct 29, 2024

@deepcs233
你好，请问Q-former的训练策略和BLIP2中使用的方法是一样的吗？

Author

CoderXuans commented Oct 29, 2024

请问Q-former可学习的权重，包含在VisionEncoder的权重中吗？

Author

CoderXuans commented Oct 29, 2024

    Qformer = BertLMHeadModel.from_pretrained(
        "bert-base-uncased", config=encoder_config
    )

请问Q-former是基于bert-base-uncased的权重吗？

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment