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.
Measures and metrics for image2image tasks. PyTorch.
| Date | Stars |
|---|---|
| 2026-07-24 | 1573 |
| 2026-07-25 | 1574 |
| 2026-07-28 | 1574 |
| 2026-07-30 | 1574 |
| 2026-08-06 | 1574 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
.. image:: https://raw.githubusercontent.com/photosynthesis-team/piq/master/docs/source/_static/piq_logo_main.png
:target: https://github.com/photosynthesis-team/piq
..
PyTorch Image Quality (PIQ) is not endorsed by Facebook, Inc.;
PyTorch, the PyTorch logo and any related marks are trademarks of Facebook, Inc.
|pypy| |conda| |flake8| |tests| |codecov| |quality_gate|
.. |pypy| image:: https://badge.fury.io/py/piq.svg
:target: https://pypi.org/project/piq/
:alt: Pypi Version
.. |conda| image:: https://anaconda.org/photosynthesis-team/piq/badges/version.svg
:target: https://anaconda.org/photosynthesis-team/piq
:alt: Conda Version
.. |flake8| image:: https://github.com/photosynthesis-team/piq/workflows/flake-8%20style%20check/badge.svg
:alt: CI flake-8 style check
.. |tests| image:: https://github.com/photosynthesis-team/piq/workflows/testing/badge.svg
:alt: CI testing
.. |codecov| image:: https://codecov.io/gh/photosynthesis-team/piq/branch/master/graph/badge.svg
:target: https://codecov.io/gh/photosynthesis-team/piq
:alt: codecov
.. |quality_gate| image:: https://sonarcloud.io/api/project_badges/measure?project=photosynthesis-team_photosynthesis.metrics&metric=alert_status
:target: https://sonarcloud.io/dashboard?id=photosynthesis-team_photosynthesis.metrics
:alt: Quality Gate Status
.. intro-section-start
`PyTorch Image Quality (PIQ) <https://github.com/photosynthesis-team/piq>`_ is a collection of measures and metrics for
image quality assessment. PIQ helps you to concentrate on your experiments without the boilerplate code.
The library contains a set of measures and metrics that is continually getting extended.
For measures/metrics that can be used as loss functions, corresponding PyTorch modules are implemented.
We provide:
* Unified interface, which is easy to use and extend.
* Written on pure PyTorch with bare minima of additional dependencies.
* Extensive user input validation. Your code will not crash in the middle of the training.
* Fast (GPU computations available) and reliable.
* Most metrics can be backpropagated for model optimization.
* Supports python 3.7-3.10.
PIQ was initially named `PhotoSynthesis.Metrics <https://pypi.org/project/photosynthesis-metrics/0.4.0/>`_.
.. intro-section-end
.. installation-section-start
Installation
------------
`PyTorch Image Quality (PIQ) <https://github.com/photosynthesis-team/piq>`_ can be installed using ``pip``, ``conda`` or ``git``.
If you use ``pip``, you can install it with:
.. code-block:: sh
$ pip install piq
If you use ``conda``, you can install it with:
.. code-block:: sh
$ conda install piq -c photosynthesis-team -c conda-forge -c PyTorch
If you want to use the latest features straight from the master, clone `PIQ repo <https://github.com/photosynthesis-team/piq>`_:
.. code-block:: sh
git clone https://github.com/photosynthesis-team/piq.git
cd piq
python setup.py install
.. installation-section-end
.. documentation-section-start
Documentation
-------------
The full documentation is available at https://piq.readthedocs.io.
.. documentation-section-end
.. usage-examples-start
Usage Examples
---------------
Image-Based metrics
^^^^^^^^^^^^^^^^^^^
The group of metrics (such as PSNR, SSIM, BRISQUE) takes an image or a pair of images as input to compute a distance between them.
We have a functional interface, which returns a metric value, and a class interface, which allows to use any metric
as a loss function.
.. code-block:: python
import torch
from piq import ssim, SSIMLoss
x = torch.rand(4, 3, 256, 256, requires_grad=True)
y = torch.rand(4, 3, 256, 256)
ssim_index: torch.Tensor = ssim(x, y, data_range=1.)
loss = SSIMLoss(data_range=1.)
output: torch.Tensor = loss(x, y)
output.backward()
For a full list of examples, see `image metrics <https://github.com/photosynthesis-team/piq/blob/master/examples/image_metrics.py>`_ examples.
Distribution-Based metricExcerpt of 16,579 characters
Read on GitHub
103
52
51
2
1
1
1
Pooya Mohammadi Kazaj · Bern University, Hospital, Inselspital · Switzerland
1
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:abaab2c5f04df864, topic:pytorch
matched fp:abaab2c5f04df864, topic:gan