pytorch-fid

library0.3.0pypypi✓ verified 85d ago

A PyTorch implementation of the Frechet Inception Distance (FID) for evaluating generative models. Version 0.3.0 is the latest stable release. The package is mature with infrequent releases.

ai-ml

pip install pytorch-fid

github ↗package ↗

INSTALL

IMPORT

SIG · PYTORCH-FID

pytorch-fid

ai-mlpythonv0.3.0

Install

73.4s avg

Import

—

Disk

5018MB

Pass rate

4/ 10

Env Coverage4 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.3.0 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✕ build_error

✓ 82.2s

py 3.11

✕ build_error

✓ 81.9s

py 3.12

✕ build_error

✓ 65.4s

py 3.13

✕ build_error

✓ 63.9s

py 3.9

✕ build_error

✕ timeout

5018MB installed

● package 5018MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

calculate_fid_given_paths

✓ from pytorch_fid import fid_score

✗ from pytorch_fid import fid_score; fid_score.calculate_fid_given_paths(paths, batch_size, device, dims, num_workers)

Example of calculating FID between two directories of images.

import torch from pytorch_fid import fid_score paths = ['path/to/real/images', 'path/to/fake/images'] # Use GPU if available device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # Calculate FID fid_value = fid_score.calculate_fid_given_paths(paths, batch_size=50, device=device, dims=2048, num_workers=8) print('FID:', fid_value)

pytorch-fid --version

Debug

Known issues

breakingIn version 0.4.0 (unreleased), the API will change; the function `calculate_fid_given_paths` will be renamed to `compute_fid` and its argument signature will change. Check the GitHub master branch for future compatibility.

fix

Use the current API (0.3.0) or monitor the repo for updates.

affects: >=0.4.0 (future)

gotchaThe Inception v3 model used by pytorch-fid is not the standard torchvision one; it uses pre-trained weights from the TensorFlow implementation. If you use your own Inception model, FID scores will be inconsistent.

fix

Always use the bundled weights (loaded automatically) from the pytorch_fid/inception.py file.

affects: all

deprecatedThe `dims` parameter accepts values 64, 192, 768, 2048. Using dims other than 2048 produces incomplete FID (not the true FID). This is a leftover from older experiments.

fix

Always use dims=2048 for standard FID.

affects: all

gotchaImage directories must contain only valid image files (jpg, png). Non-image files or corrupted images cause silent failures or crashes.

fix

Sanitize directories to contain only supported image formats.

affects: all

Upgrade

Version history

0.3.0latest on PyPI · released Jan 5, 2023

Audit

Dependencies

torchrequiredCore dependency for PyTorch operations

torchvisionrequiredProvides Inception v3 model and image transforms

numpyrequiredUsed for matrix operations and statistics

scipyrequiredUsed for FID computation (matrix square root and trace)

Agent activity

14 hits · last 30 days

node

Amazon

OpenAI (training)

Resources

githubhttps://github.com/mseitzer/pytorch-fid ↗

packagehttps://pypi.org/project/pytorch-fid/ ↗