原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
In algorithm 32.2 we train the denoiser using a loss L, which could be the L2 distance. In many diffusion models, fθ is instead trained to output the parameters (mean and variance) as a Gaussian density model fit to the data. This formulation yields useful probabilistic interpretations (in fact, such a diffusion model can be framed as a variational autoencoder, which we will see in
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c032.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8