# raghakot/keras-resnet

Residual networks implementation using Keras-1.0 functional API

Repository: https://github.com/raghakot/keras-resnet
Canonical: https://ross.abutalabs.com/products/keras-resnet
Language: Python
License: NOASSERTION
License Family: other
Topics: deep-learning, keras, resnet
Last push: 2021-01-12T11:01:26+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": 3789, "days_push": 2059, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1389, forks 595 (observed 2026-08-28T04:04:35.341688+00:00)

## What it is
A Keras implementation of Residual Networks (ResNet) using the Keras 1.0 functional API, supporting both Theano and TensorFlow backends. It provides a ResNetBuilder factory to construct standard ResNet architectures like ResNet18 and ResNet50 with custom input shapes.

## Use cases
- build resnet models in keras
- train a resnet on cifar10
- implement residual networks for image classification
- create custom resnet architectures with my own input shape
- use bottleneck and basic residual blocks in keras

## When to choose
- you are working with legacy Keras 1.x codebases and need a reference ResNet implementation
- you want a simple, readable ResNet implementation to study or modify

## When to avoid
- you are using modern TensorFlow/Keras 2.x, where ResNet is built into keras.applications
- you need actively maintained code or support for recent Keras versions
- you need state-of-the-art CIFAR-10 accuracy out of the box

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, machine-learning
- domain: deep-learning, computer-vision, image-processing
- platform: python
- tags: resnet, keras, neural-networks, image-classification, convolutional-networks

## Member repositories
- raghakot/keras-resnet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:35.341688+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 2026-08-30T04:39:43.168787+00:00, confidence not recorded.
  - readme: https://github.com/raghakot/keras-resnet (fetched 2026-08-28T04:04:35.341688+00:00, sha 436093137159)
- Data as of 2026-08-30T08:39:29.467469+00:00.