Skip to main content

High-fidelity performance metrics for generative models in PyTorch

Project description


Evaluation of generative models such as GANs is an important part of the deep learning research.
In the domain of 2D image generation, three approaches became widely spread: Inception Score
(aka IS), Fréchet Inception Distance (aka FID), and Kernel Inception Distance (aka KID).

These metrics, despite having a clear mathematical and algorithmic description, were initially
implemented in TensorFlow, and inherited a few properties of the framework itself and the code
they relied upon. These design decisions were effectively baked into the evaluation protocol and
became an inherent part of the metrics specification. As a result, researchers wishing to
compare against state of the art in generative modeling are forced to perform evaluation using
codebases of the original metric authors. Reimplementations of metrics in PyTorch and other
frameworks exist, but they do not provide a proper level of fidelity, thus making them
unsuitable for reporting results and comparing to other methods.

This software aims to provide epsilon-exact implementations of the said metrics in PyTorch, and thus
remove inconveniences associated with generative models evaluation and development.
Find more details and the most up-to-date information on the project webpage:
https://www.github.com/toshas/torch-fidelity


Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

torch_fidelity-0.2.0.tar.gz (22.1 kB view hashes)

Uploaded Source

Built Distribution

torch_fidelity-0.2.0-py3-none-any.whl (22.7 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page