Po-Hsun-Su/pytorch-ssim
pytorch structural similarity (SSIM) loss observed · 2026-08-28
Health v2 · maintenance only
32/100
- Activity 0
- Release rhythm 35
- Longevity 100
Flags: no_releases no_license
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 3311
- days_rel: n/a
- days_push: 923
- n_releases_24m: 0
Adoption not part of the score
1949 stars · 367 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
A small PyTorch library providing a differentiable structural similarity (SSIM) index and SSIM loss module for image comparison. It can be used as a loss function in image reconstruction and generation tasks.
Use cases
- compute SSIM between two images in PyTorch
- use SSIM as a differentiable loss for training image reconstruction models
- optimize an image to maximize structural similarity to a target
- evaluate perceptual similarity in image processing pipelines
When to choose
- you need a simple, copy-paste SSIM loss for an older PyTorch project
- you want a minimal dependency-free SSIM implementation
When to avoid
- you are on modern PyTorch — the code is broken with recent versions and the repo is unmaintained
- you need maintained alternatives like pytorch-msssim or torchmetrics SSIM
Facets
library · maturity abandoned
image-processing machine-learning image-processing deep-learning python ssim pytorch loss-function differentiable not-maintained
2 sources
- readme: https://github.com/Po-Hsun-Su/pytorch-ssim · fetched 2026-08-28 · d6d7eadf44be
- registry_pypi: https://pypi.org/pypi/pytorch-ssim/json · fetched 2026-08-29 · f8bf520d4b05
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| Po-Hsun-Su/pytorch-ssim | main | 32 |
For agents
markdown · JSON · MCP: product_card(name="Po-Hsun-Su/pytorch-ssim")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem