# sanghyun-son/EDSR-PyTorch

PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

Repository: https://github.com/sanghyun-son/EDSR-PyTorch
Canonical: https://ross.abutalabs.com/products/edsr-pytorch
Language: Python
License: MIT
License Family: permissive
Last push: 2023-01-03T01:47:11+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3270, "days_push": 1339, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2627, forks 682 (observed 2026-08-28T04:07:05.427001+00:00)

## What it is
Official PyTorch implementation of EDSR (Enhanced Deep Residual Networks for Single Image Super-Resolution, CVPRW 2017). It provides training and evaluation scripts plus pre-trained models for upscaling images at multiple scales.

## Use cases
- upscale low-resolution images with a deep learning model
- train a super-resolution network from scratch
- reproduce EDSR paper results
- apply a pretrained super-resolution model to my photos
- benchmark image super-resolution models

## When to choose
- you need a well-cited, reference implementation of EDSR for research
- you want pretrained models for 2x/3x/4x image upscaling
- you want to train or fine-tune a super-resolution model in PyTorch

## When to avoid
- you need MDSR support on recent PyTorch versions (temporarily disabled on master)
- you want a production-ready image upscaling service with an API
- you need the latest state-of-the-art super-resolution architectures

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning
- platform: python, windows
- tags: super-resolution, pytorch, edsr, image-upscaling, computer-vision-research, pretrained-models, linux, macos

## Member repositories
- sanghyun-son/EDSR-PyTorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:05.427001+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:19:45.433847+00:00, confidence not recorded.
  - readme: https://github.com/sanghyun-son/EDSR-PyTorch (fetched 2026-08-28T04:07:05.427001+00:00, sha 716c8ae7e4f6)
- Data as of 2026-08-30T08:39:29.467469+00:00.