# krasserm/super-resolution

Tensorflow 2.x based implementation of EDSR, WDSR and SRGAN for single image super-resolution

Repository: https://github.com/krasserm/super-resolution
Canonical: https://ross.abutalabs.com/products/super-resolution
Language: Python
License: Apache-2.0
License Family: permissive
Topics: wdsr, edsr, keras, super-resolution, single-image-super-resolution, srgan, tensorflow, tensorflow2
Last push: 2022-05-13T11:47:05+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2877, "days_push": 1573, "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 1511, forks 342 (observed 2026-08-28T04:04:55.931750+00:00)

## What it is
A TensorFlow 2.x implementation of EDSR, WDSR, and SRGAN models for single image super-resolution, with a high-level training API and DIV2K dataset support. It includes pre-trained weights and example notebooks for training, fine-tuning, and upscaling images.

## Use cases
- upscale low-resolution images with deep learning
- train an EDSR or WDSR super-resolution model
- fine-tune a super-resolution model with SRGAN for photo-realistic results
- reproduce NTIRE challenge super-resolution papers
- increase image resolution 2x, 3x, 4x, or 8x in Python

## When to choose
- you want a TensorFlow 2.x/Keras codebase for single-image super-resolution
- you need to train or fine-tune EDSR, WDSR, or SRGAN on DIV2K or custom data
- you want ready-to-use pre-trained weights for quick upscaling experiments

## When to avoid
- you need a production-ready image upscaling service or GUI rather than a research library
- you work outside the TensorFlow/Keras ecosystem (e.g. prefer PyTorch)
- you need actively maintained code with recent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, deep-learning
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python
- tags: super-resolution, tensorflow2, keras, edsr, wdsr, srgan, div2k, image-upscaling, gpu

## Member repositories
- krasserm/super-resolution (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:55.931750+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 2026-08-30T04:32:23.593784+00:00, confidence not recorded.
  - readme: https://github.com/krasserm/super-resolution (fetched 2026-08-28T04:04:55.931750+00:00, sha 8297d624490b)
- Data as of 2026-08-30T08:39:29.467469+00:00.