{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/6"}],"enrichment":{"capability":"Computes fast, differentiable SSIM and MS-SSIM metrics for PyTorch tensors using separable Gaussian kernels, enabling efficient image quality assessment and loss functions for neural networks.","skillfed_tags":["image-metrics","loss-functions","computer-vision"],"use_cases":["Use as a loss function in autoencoders or image-to-image translation networks (e.g., super-resolution, denoising).","Evaluate image generation quality in GANs or diffusion models by computing MS-SSIM between generated and reference images.","Benchmark image compression algorithms by measuring perceptual similarity before and after compression.","Monitor image reconstruction fidelity in medical imaging or scientific applications where structural detail matters more than pixel values.","Compare image quality across different preprocessing or augmentation pipelines in computer vision workflows."],"what_it_does":"pytorch-msssim provides PyTorch implementations of SSIM (Structural Similarity Index) and MS-SSIM (Multi-Scale SSIM), two perceptual image quality metrics commonly used to measure similarity between images. Unlike naive implementations, it uses separable Gaussian kernels\u2014decomposing 2D convolutions into two 1D operations\u2014which reduces computational complexity and improves cache locality, making it significantly faster than alternatives like TensorFlow or scikit-image while remaining fully differentiable for use as a loss function in neural networks.\n\nThe package is typically used in image generation, reconstruction, and compression tasks where pixel-level losses (like L2) are inadequate. You can call ssim() and ms_ssim() as functions for one-off computations, or instantiate SSIM and MS_SSIM modules to reuse Gaussian kernels across multiple forward passes. It handles both single images and batches, supports grayscale and RGB, and includes 3D image support; inputs must be denormalized to a known range (e.g., [0, 255] or [0, 1]) for correct results.","worth_installing":"Yes, if you need a fast, differentiable SSIM/MS-SSIM implementation for PyTorch. The low install friction, permissive license, and proven performance (benchmarked against TensorFlow and scikit-image) make it a solid choice for image quality assessment and loss functions. Dormant maintenance is a minor concern\u2014the core algorithm is stable and unlikely to need updates, but expect no active support for new PyTorch or Python versions."},"id":"pytorch-msssim","links":{"html":"https://skillfed.io/packages/pytorch-msssim","md":"https://skillfed.io/packages/pytorch-msssim.md","pypi":"https://pypi.org/project/pytorch-msssim/"},"maintenance":{"status":"dormant"},"meta":{"latest_release":"2023-05-25","license_spdx":null,"license_treatment":"permissive","name":"pytorch-msssim","python_support":"unspecified","summary":"Fast and differentiable MS-SSIM and SSIM for pytorch."},"popularity":{"monthly_downloads":300858,"position":7840,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"1.0.0"}