Better NN architectures #1442
Labels
enhancement
New feature or request
hackathon
score-matching-performance
Improving the performance of score- and flow-matching methods
🚀 Feature Request
Unlike NPE, score and flow matching approaches are highly sensitive to the neural network architecture used to estimate the corresponding vector field. It is well-known that diffusion models, for example, tend to work best with specialized architectures like U-Nets for images (and other similarly specialized structures).
Describe the solution you'd like
To address this, the following steps should be completed:
pytest --bm
orpytest --bm -n
for multiprocessing (if you have a capable CPU).Additional Context
The aim is to enhance the performance of score and flow matching by incorporating more suitable neural network architectures, providing better results than the default MLPs/ResNets currently used.
The text was updated successfully, but these errors were encountered: