# liuzhuang13/DenseNet

Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).

Repository: https://github.com/liuzhuang13/DenseNet
Canonical: https://ross.abutalabs.com/products/densenet
Language: Lua
License: BSD-3-Clause
License Family: permissive
Topics: deep-learning
Last push: 2024-01-09T13:15:40+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": 3661, "days_push": 967, "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 4869, forks 1063 (observed 2026-08-28T04:09:01.620498+00:00)

## What it is
Reference implementation of DenseNet (Densely Connected Convolutional Networks), the CVPR 2017 Best Paper Award-winning CNN architecture, written in Lua on the Torch framework. It includes a memory-efficient implementation and links to community ports in PyTorch, TensorFlow, Keras, and other frameworks.

## Use cases
- train a DenseNet image classification model
- reproduce the CVPR 2017 DenseNet paper results
- study densely connected convolutional network architecture code
- get a memory-efficient DenseNet implementation
- classify images with a densely connected CNN

## When to choose
- you need the original reference implementation of DenseNet
- you are doing research on or reproducing the DenseNet paper
- you specifically work with the Torch (Lua) deep learning stack

## When to avoid
- you want to use DenseNet in production with modern tooling - use torchvision or Keras implementations instead
- you do not use the legacy Torch/Lua framework
- you need actively maintained code with recent updates and support

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, machine-learning, image-processing, computer-vision
- domain: deep-learning, computer-vision, machine-learning, image-processing
- platform: lua
- tags: densenet, convolutional-networks, torch, research-code, cvpr-2017, image-classification, gpu, linux

## Member repositories
- liuzhuang13/DenseNet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:01.620498+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 2026-08-29T18:18:20.065915+00:00, confidence not recorded.
  - readme: https://github.com/liuzhuang13/DenseNet (fetched 2026-08-28T04:09:01.620498+00:00, sha ca054dce1112)
- Data as of 2026-08-30T08:39:29.467469+00:00.