# KaimingHe/deep-residual-networks

Deep Residual Learning for Image Recognition

Repository: https://github.com/KaimingHe/deep-residual-networks
Canonical: https://ross.abutalabs.com/products/deep-residual-networks
License: MIT
License Family: permissive
Last push: 2017-10-28T15:26:22+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": 3866, "days_push": 3231, "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 6753, forks 2231 (observed 2026-08-28T04:09:48.331846+00:00)

## What it is
The official repository for the original ResNet-50, ResNet-101, and ResNet-152 models from the paper 'Deep Residual Learning for Image Recognition', converted to Caffe format. It provides pretrained models used to win ILSVRC and COCO 2015 competitions, intended for testing or fine-tuning rather than training.

## Use cases
- download pretrained resnet-50 models for image classification
- fine-tune resnet on my own image dataset
- reproduce imagenet classification results from the resnet paper
- use resnet as a feature extractor backbone for object detection
- compare caffe model weights for resnet-101 and resnet-152

## When to choose
- you need the original, canonical ResNet model weights from the authors
- you work in Caffe and want pretrained ResNets for testing or fine-tuning
- you want to cite or reproduce the exact ILSVRC/COCO 2015 winning models

## When to avoid
- you want training code - use third-party re-implementations like fb.resnet.torch or PyTorch/TensorFlow versions
- you work in modern frameworks like PyTorch or TensorFlow rather than Caffe
- you need actively maintained code with recent updates

## Facets
- artifact type: dataset
- maturity: maintenance
- function: deep-learning, machine-learning, image-processing, computer-vision
- domain: deep-learning, computer-vision, image-processing, machine-learning
- platform: cpp
- tags: resnet, caffe, pretrained-models, image-classification, imagenet, research-paper-models, gpu, linux

## Member repositories
- KaimingHe/deep-residual-networks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:48.331846+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 2026-08-29T17:42:34.880256+00:00, confidence not recorded.
  - readme: https://github.com/KaimingHe/deep-residual-networks (fetched 2026-08-28T04:09:48.331846+00:00, sha b710989f5886)
- Data as of 2026-08-30T08:39:29.467469+00:00.