# ry/tensorflow-resnet

ResNet model in TensorFlow

Repository: https://github.com/ry/tensorflow-resnet
Canonical: https://ross.abutalabs.com/products/tensorflow-resnet
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2018-06-16T02:54:27+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3911, "days_push": 3000, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1665, forks 620 (observed 2026-08-28T04:05:18.968162+00:00)

## What it is
An implementation of the ResNet deep residual learning model in TensorFlow, including a tool to convert Kaiming He's published Caffe pretrained weights for use in TensorFlow. The project is explicitly deprecated and does not run on modern TensorFlow.

## Use cases
- train a ResNet model on CIFAR-10 or ImageNet in TensorFlow
- convert pretrained Caffe ResNet weights to TensorFlow format
- use a pretrained ResNet as a foundation for image classification experiments
- experiment with ResNet architecture variants like stochastic depth
- run fully convolutional ResNet on arbitrary input sizes

## When to choose
- you need to load He et al's original Caffe ResNet weights into TensorFlow
- you are studying historical ResNet implementations or working with legacy TensorFlow 0.8-era code

## When to avoid
- you are using any modern version of TensorFlow
- you want a maintained ResNet implementation - use tf.contrib.slim resnet_v1 or Keras applications instead
- you need out-of-the-box training on CIFAR-10/100 or ImageNet - the implementation is incomplete

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

## Member repositories
- ry/tensorflow-resnet (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:18.968162+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 2026-08-30T03:44:27.253810+00:00, confidence not recorded.
  - readme: https://github.com/ry/tensorflow-resnet (fetched 2026-08-28T04:05:18.968162+00:00, sha 8114c756b78b)
- Data as of 2026-08-30T08:39:29.467469+00:00.