Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
High-fidelity performance metrics for generative models in PyTorch
| Date | Stars |
|---|---|
| 2026-07-24 | 1195 |
| 2026-07-25 | 1196 |
| 2026-07-28 | 1196 |
| 2026-07-30 | 1196 |
| 2026-08-06 | 1196 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
 [](https://torch-fidelity.readthedocs.io/en/latest/?badge=latest) [](https://circleci.com/gh/toshas/torch-fidelity) [](https://pypi.org/project/torch-fidelity/) [](https://pepy.tech/project/torch-fidelity) [](https://twitter.com/antonobukhov1) This repository provides **precise**, **efficient**, and **extensible** implementations of the popular metrics for generative model evaluation, including: - Inception Score ([ISC](https://arxiv.org/pdf/1606.03498.pdf)) - Fréchet Inception Distance ([FID](https://arxiv.org/pdf/1706.08500.pdf)) - Kernel Inception Distance ([KID](https://arxiv.org/pdf/1801.01401.pdf)) - Precision and Recall ([PRC](https://arxiv.org/pdf/1904.06991.pdf)) - Perceptual Path Length ([PPL](https://arxiv.org/pdf/1812.04948.pdf)) - Monge Inception Distance ([MIND](https://arxiv.org/pdf/2605.06797.pdf)) **Numerical Precision**: Unlike many other reimplementations, the values produced by torch-fidelity match reference implementations up to floating point's machine precision. This allows using torch-fidelity for reporting metrics in papers instead of scattered and slow reference implementations. [Read more about numerical precision](https://torch-fidelity.readthedocs.io/en/latest/precision.html) **Efficiency**: Feature sharing between different metrics saves recomputation time, and an additional caching level avoids recomputing features and statistics whenever possible. High efficiency allows using torch-fidelity in the training loop, for example at the end of every epoch. [Read more about efficiency](https://torch-fidelity.readthedocs.io/en/latest/miscellaneous.html) **Extensibility**: Going beyond 2D image generation is easy due to high modularity and abstraction of the metrics from input data, models, and feature extractors. Register a custom feature extractor to evaluate any modality — video, audio, 3D volumes, or anything else with a suitable learned representation. [Read more about extensibility](https://torch-fidelity.readthedocs.io/en/latest/extensibility.html) **TLDR; fast and reliable generative model evaluation in PyTorch** ## Installation ```shell script pip install torch-fidelity ``` See also: [Installing the latest GitHub code](https://torch-fidelity.readthedocs.io/en/latest/installation.html#nightly-version) ## Usage Examples with Command Line Below are three examples of using torch-fidelity to evaluate metrics from the command line. See more examples in the documentation. ### Simple Inception Score of CIFAR-10 training split: ```shell script > fidelity --gpu 0 --isc --input1 cifar10-train inception_score_mean: 11.23678 inception_score_std: 0.09514061 ``` ### Medium Inception Score of a directory of images stored in `~/images/`: ```shell script > fidelity --gpu 0 --isc --input1 ~/images/ ``` ### Pro Efficient computation of ISC and PPL for `input1`, and FID, KID, PRC, MIND between a generative model stored in `~/generator.onnx` and CIFAR-10 training split: ```shell script > fidelity \ --gpu 0 \ --isc \ --fid \ --kid \ --ppl \ --prc \ --mind \ --input1 ~/generator.onnx \ --input1-model-z-type normal \ --input1-model-z-size 128 \ --input1-model-num-samples 50000 \ --input2 cifar10-train ``` See also: [Other usage examples](https://torch-fidelity.readthedocs.io/en/latest/usage_cmd.html) ## Quick Start with Python API When it comes to tracking the performance of generative models as they train, evaluating metrics after every epoch becomes prohibitively expensive due to long computat
Excerpt of 6,924 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ceb99f898805ddda, topic:gan, readme:image generation
matched fp:ceb99f898805ddda, topic:pytorch
matched fp:ceb99f898805ddda, topic:evaluation
