# fyu/drn

Dilated Residual Networks

Repository: https://github.com/fyu/drn
Canonical: https://ross.abutalabs.com/products/drn
Homepage: https://www.vis.xyz/pub/drn
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2020-03-09T19:11:52+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": 3278, "days_push": 2368, "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 1102, forks 218 (observed 2026-08-28T04:03:35.951961+00:00)

## What it is
A PyTorch library implementing Dilated Residual Networks (DRN), which combine dilated convolutions with residual networks for image classification and semantic segmentation. It provides pretrained models that outperform ResNet with fewer parameters, including state-of-the-art segmentation results on Cityscapes.

## Use cases
- classify images with dilated residual networks
- semantic segmentation of street scenes on Cityscapes
- load pretrained DRN models in PyTorch
- generate high-resolution class activation maps for weakly supervised object localization
- train models with synchronized BatchNorm across multiple GPUs
- compare efficient network architectures against ResNet baselines

## When to avoid
- you need a maintained library with recent updates (last release 2020)
- you work outside PyTorch, e.g. TensorFlow or JAX
- you need modern architectures like transformers or vision foundation models

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, deep-learning, image-processing
- platform: python
- tags: pytorch, dilated-convolutions, residual-networks, semantic-segmentation, image-classification, pretrained-models, gpu

## Member repositories
- fyu/drn (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:35.951961+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 2026-08-30T06:45:38.006022+00:00, confidence not recorded.
  - readme: https://github.com/fyu/drn (fetched 2026-08-28T04:03:35.951961+00:00, sha 93065af47b7f)
- Data as of 2026-08-30T08:39:29.467469+00:00.