Repository files navigation

PIQA is a collection of PyTorch metrics for image quality assessment in various image processing tasks such as generation, denoising, super-resolution, interpolation, etc. It focuses on the efficiency, conciseness and understandability of its (sub-)modules, such that anyone can easily reuse and/or adapt them to its needs.

PIQA should be pronouncedpika (like Pikachu ⚡️)

Thepiqa package is available onPyPI, which means it is installable viapip.

pip install piqa

Alternatively, if you need the latest features, you can install it from the repository.

pip install git+https://github.com/francois-rozet/piqa

Inpiqa, each metric is associated to a class, child oftorch.nn.Module, which has to be instantiated to evaluate the metric. All metrics are differentiable and support CPU and GPU (CUDA).

importtorchimportpiqa# PSNRx=torch.rand(5,3,256,256)y=torch.rand(5,3,256,256)psnr=piqa.PSNR()l=psnr(x,y)# SSIMx=torch.rand(5,3,256,256,requires_grad=True).cuda()y=torch.rand(5,3,256,256).cuda()ssim=piqa.SSIM().cuda()l=1-ssim(x,y)l.backward()

Liketorch.nn built-in components, these classes are based on functional definitions of the metrics, which are less user-friendly, but more versatile.

frompiqa.ssimimportssimfrompiqa.utils.functionalimportgaussian_kernelkernel=gaussian_kernel(11,sigma=1.5).repeat(3,1,1)ss,cs=ssim(x,y,kernel=kernel)

For more information, check out the documentation atpiqa.readthedocs.io.

All metrics ofpiqa supportPyTorch's tracing, which optimizes their execution, especially on GPU.

ssim=piqa.SSIM().cuda()ssim_traced=torch.jit.trace(ssim, (x,y))l=1-ssim_traced(x,y)# should be faster ¯\_(ツ)_/¯

PIQA uses type assertions to raise meaningful messages when a metric doesn't receive an input of the expected type. This feature eases a lot early prototyping and debugging, but it might hurt a little the performances. If you need the absolute best performances, the assertions can be disabled with the Python flag-O. For example,

python -O your_awesome_code_using_piqa.py

Alternatively, you can disable PIQA's type assertions within your code with

piqa.utils.set_debug(False)

If you have a question, an issue or would like to contribute, please read ourcontributing guidelines.