PyTorch Image Quality Assessement package
PIQA 1.3.0 drops its custom complex module in favor of torch.complex
, which is stable since PyTorch 1.12. Accordingly, the support for torch <= 1.11 has been dropped.
Full Changelog: https://github.com/francois-rozet/piqa/compare/v1.2.2...v1.3.0
The documentation has been refactored and is now generated using Sphinx and Furo. Check it out at francois-rozet.github.io/piqa/.
torch.linalg.norm
by l2_norm
(48ec8c41f6207e02a317a9d30e504c0d19cd071d)RuntimeError
while using conv1d
for 2 or 3-d convolutions with PyTorch 1.11 (7a56439ca5b67df145650fa6688b8eb237a09ba6)PIQA 1.1.7 requires the torch.fft
module released with PyTorch 1.8.0.
VSI
Visual Saliency-based Index (0125e904ff74c1339798a8b46b003d27184ff199)FSIM
Feature Similarity (0125e904ff74c1339798a8b46b003d27184ff199)SSIM
(76415a95212c203225cd4eb9fbc8e437e38ebcd2)FSIM
, GMSD
, HaarPSI
, MDSI
and VSI
(9fedf9f11b1e0a0a499ccc54fac933c22f0c86e3)utils.complex
submodule (d098f4d00f183050267d6a55dcaf455e08d41405)Object-oriented components (PSNR
, SSIM
, ...) now use type assertions to raise meaningful error messages. See the "Assert" section in the README for more information.
In this release, the API has been heavily redesigned and simplified.
piqa
now directly gives access to the object-oriented metrics (5994e349d4c140877e560b18c2a51307e61575fc)v1.1.0 | v1.1.3 |
---|---|
|
|
piqa.utils
module was divided in three sub-modules (5994e349d4c140877e560b18c2a51307e61575fc)
piqa.utils.functional
regroups the convolution and kernel helperspiqa.utils.complex
is an API to manipulate "factice" complex tensorspiqa.utils.color
handles the color-space conversionstensor_norm
& normalize_tensor
) were dropped in favor of torch.linalg.norm
(f7440076a27f8415dca1f067e3c6b49cd8924c2e)PIQA now has an official logo and a banner π
MDSI
automatic differentiation (f73b13c73fdd01caf319f5042acfcfb9aa36c0fa, c6d924d68af9d914d3a3cd26bbbd114496ad402c)PIQA 1.1.0 requires PyTorch 1.7.0 or above.
MS-GMSD
Multi-Scale Gradient Magnitude Similarity Deviation (2364fbc25389076a813d884709350cf5a1c221d3)HaarPSI
Haar Perceptual Similarity Index (3227b269a4de91619c9c83a3d8a1d20334ac6d39)lpips.LPIPS
results (43ae9d763bb073f6c127950d9c42da3b57de4378)RuntimeError
in mdsi.mdsi
on CUDA (0e890000c3cdf8da7a892ff962bc9f00097c0bdc)FileNotFoundError
when loading lpips.LPIPS
weights (200460a180b7eb416544a3e33d1d756993ab5213)tv.tv
(fe983b6a2b23b8b63db3469cf9d2002821a70934)Examples were added in the docstrings for a better user experience. They also acts as unit tests thanks to the doctest
and unittest
libraries.
GMSD
Gradient Magnitude Similarity Deviation (8c1e1dcb9e330a564e3ef750b44394dfbbd3c6f0)MDSI
Mean Deviation Similarity Index (e79b340d9c4a57e6a66cd2e3b6b2e63d5ab3d974)**kwargs
) to simplify function signatures (3d1fd4c1acbc91acec0f65c4107adbb0f8b41f5a)if elif else
statement by a function (c9719b2f284f67fe73f33f7e4be4d543371347c3)First release of the Simple PyTorch Image Quality (SPIQ) package π
PSNR
Peak Signal-to-Noise Ratio (d79e5f32981350475c6446fcba9610fd631ecc07)SSIM
Structural Similarity (c1addd271684dbd98af339a4e020932fb92e6026)MS-SSIM
Multi-Scale Structural Similarity (be1821f23c0c81a6ee937dff125c5025042313f7)TV
Total Variation (2be72f6bd848eada823ae6f210fea1f06967111d)LPIPS
Learned Perceptual Image Patch Similarity (6a1703171fe8c296c597c937bc4e986a971ff6df)pdoc
This package is under the MIT License.