AI engineering glossary · Generative media multimodal
What is FID (Fréchet Inception Distance)?
Fréchet Inception Distance (also called FID): A metric for generated images that compares the statistics (mean and covariance) of deep features from real and generated sets using a pretrained Inception network. Lower values mean the generated distribution is closer to the real one.
Fréchet Inception Distance: an example
A model with FID 8 on a face dataset matches real-image statistics more closely than a model scoring 25.
Related terms
More Generative media multimodal terms
- Generative adversarial network
- Grapheme-to-phoneme
- Guidance scale
- Image captioning
- Image tokenizer
- Image-to-image translation
- Inception Score
- Inpainting
Where you learn it
Fréchet Inception Distance is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.