search

yang-song / score_sde_pytorch

PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
https://arxiv.org/abs/2011.13456
Apache License 2.0
1.58k stars 295 forks source link

How to calculate the score of a new unseen datapoint by a score based diffusion model? #55

Open rajoy99 opened 5 months ago

rajoy99 commented 5 months ago

I have a pretrained score based diffusion model trained on 64X64 images. Now I want to calculate the score of a new image(of same dimension) through this pre-trained neural network.

The score network takes two inputs :

  1. x_t : Sample at timestamp t
  2. t : timestamp How should I calculate the score of a new image via this pre-trained neural network ?