Skip to content

Conversation

@5Hyeons
Copy link
Owner

@5Hyeons 5Hyeons commented Aug 22, 2024

Changed the method of integrating historical information features into the diffusion model.
Previously, historical information features were processed through a GNN, then a style was predicted using a style_predictor, and the result was concatenated with h_bert before being fed into the diffusion model.

This has been updated to directly use the historical information features as a context condition in the diffusion model, leveraging cross-attention instead of concatenation.


기존에는 historical information feature를 GNN을 통해 처리한 후, style_predictor를 사용하여 스타일을 추론하고, 이를 h_bert와 concat하여 diffusion model에 입력하는 방식을 사용했습니다.

이를 변경하여 historical information feature를 diffusion 모델의 context condition으로 직접 사용하고, concat 대신 cross-attention 방식을 활용하도록 수정했습니다.

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

Successfully merging this pull request may close these issues.

2 participants