It calculates the FID score between source and target images
Project description
Project Description
Frechet Inception Distance (FID score)
Install
pip install fid-score
Requirements
pytorch >= 1.2.0
torchvision >= 0.3.0
Usage:
from fid_score.fid_score import FiDScore
fid = FidScore(paths, device, batch_size)
score = fid.calculate_fid_score()
Arguments
fid = FidScore(paths, device, batch_size)
paths = ['path of source image dir', 'path of target image dir']
device = torch.device('cuda:0') or default: torch.device('cpu')
batch_size = batch size
References
1. FID was introduced by Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler and Sepp Hochreiter in
"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium"
2. The original implementation is by the Institute of Bioinformatics, JKU Linz, licensed under the Apache License 2.0.
See https://github.com/bioinf-jku/TTUR.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
fid_score-0.1.3.tar.gz
(5.7 kB
view hashes)
Built Distribution
Close
Hashes for fid_score-0.1.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c2e49337726d7922dec8e3e4d0663b0fb94f62fd97f6a248e4682cbc1965f26d |
|
MD5 | a858b550c7b10e8197c8460bbaa3d0cb |
|
BLAKE2b-256 | 0e260cfa28529b55b5c96b5e73ca5ac6280f195b2f5e49108e15f4503b85811b |