Releases: francois-rozet/piqa
PIQA v1.3.0
π₯ Breaking news
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.
β¨ What's new
- New FrΓ©chet Inception Distance (FID) metric (8950f5e)
- All metrics now support PyTorch's tracing (d233ef8)
- The documentation has been refreshed and moved to Read the Docs (d233ef8, d670de1)
- New contributing guidelines (7ebd950)
π Bug fixes
Full Changelog: v1.2.2...v1.3.0
PIQA v1.2.2
π Documentation
The documentation has been refactored and is now generated using Sphinx and Furo. Check it out at francois-rozet.github.io/piqa/.
β‘οΈ Improvements
π Bug fixes
- Fix
RuntimeError
while usingconv1d
for 2 or 3-d convolutions with PyTorch 1.11 (7a56439)
PIQA v1.1.7
β¬οΈ Dependencies
PIQA 1.1.7 requires the torch.fft
module released with PyTorch 1.8.0.
β¨ Metrics
β‘οΈ Improvements
- Make padding optional in
SSIM
(76415a9) - Make downsampling optional in
FSIM
,GMSD
,HaarPSI
,MDSI
andVSI
(9fedf9f)
π Bug fixes
- Fix JITting for
utils.complex
submodule (d098f4d)
PIQA v1.1.3
πΈ Type assertions
Object-oriented components (PSNR
, SSIM
, ...) now use type assertions to raise meaningful error messages. See the "Assert" section in the README for more information.
β»οΈ Refactor
In this release, the API has been heavily redesigned and simplified.
- The "user-friendly" functionals to compute the metrics were dropped in favor of object-oriented metrics (5994e34)
- Importing
piqa
now directly gives access to the object-oriented metrics (5994e34)
v1.1.0 | v1.1.3 |
---|---|
>>> from piqa import ssim
>>> criterion = ssim.SSIM()
>>> criterion(x, y)
tensor(...) |
>>> import piqa
>>> criterion = piqa.SSIM()
>>> criterion(x, y)
tensor(...) |
- The
piqa.utils
module was divided in three sub-modules (5994e34)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 conversions
- JITing is now an option which can be enabled/disabled (f467070)
- Custom normalization functionals (
tensor_norm
&normalize_tensor
) were dropped in favor oftorch.linalg.norm
(f744007)
PIQA v1.1.0
PIQA now has an official logo and a banner π
β‘οΈ Improvements
- Update core components to support PyTorch JIT (c8ac2c3)
- Optimize Gaussian blur with separable convolutions (c8ac2c3)
- Simplify some components (ba07335, 0b5a85e, 785b449)
π Bug fixes
π Documentation
- Add table of available metrics in README
- Refresh the full documentation (types, shapes, etc.)
- Add mathematical definitions in docstrings
β¬οΈ Dependencies
PIQA 1.1.0 requires PyTorch 1.7.0 or above.
PIQA v1.0.7
PIQA v1.0.5
π Critical fixes
- Pin correct dependencies (3860c5c)
- Fix
FileNotFoundError
when loadinglpips.LPIPS
weights (200460a) - Fix dimension mismatch in
tv.tv
(fe983b6)
β Unit tests
Examples were added in the docstrings for a better user experience. They also acts as unit tests thanks to the doctest
and unittest
libraries.
PIQA v1.0.0
π¦ Package
- The package is renamed to PyTorch Image Quality Assessment (PIQA)
- PIQA is deployed on PyPi
β¨ Metrics
GMSD
Gradient Magnitude Similarity Deviation (8c1e1dc)MDSI
Mean Deviation Similarity Index (e79b340)
β‘οΈ Improvements
- Use cascading named arguments (
**kwargs
) to simplify function signatures (3d1fd4c) - Replace duplicated reduction
if elif else
statement by a function (c9719b2) - ...
π Documentation
- Update code style to be compliant with the Google Python Style
- Update docstrings for consistency with PyTorch docs
SPIQ v0.0.2-beta
First release of the Simple PyTorch Image Quality (SPIQ) package π
β¨ Metrics
PSNR
Peak Signal-to-Noise Ratio (d79e5f3)SSIM
Structural Similarity (c1addd2)MS-SSIM
Multi-Scale Structural Similarity (be1821f)TV
Total Variation (2be72f6)LPIPS
Learned Perceptual Image Patch Similarity (6a17031)
π Documentation
- Installation instructions and snippet for getting started in README
- Documentation fully contained in the components' docstrings
- Documentation website generated automatically from the docstrings using
pdoc
π License
This package is under the MIT License.