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

Gen.encoder为什么存在 #199

Open

125jx opened this issue Mar 13, 2025 · 1 comment

125jx commented Mar 13, 2025

Gen.encoder为什么存在？我是一名小白，我觉得根据文字生成图不是只有文字吗？为什么还需要一个Gen.encoder进行图像编码

HaFred commented Mar 16, 2025

https://github.com/deepseek-ai/Janus/blob/main/generation_inference.py#L98
During inference, gen_vision_model is only used for decoding generated image tokens into image pixels. Its encoder is only used during training, of which you may find more details in the report.

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