# ramprs/grad-cam

[ICCV 2017] Torch code for Grad-CAM

Repository: https://github.com/ramprs/grad-cam
Canonical: https://ross.abutalabs.com/products/grad-cam
Homepage: https://arxiv.org/abs/1610.02391
Language: Lua
License Family: other
Topics: iccv17, grad-cam, interpretability, convolutional-neural-networks, deep-learning, heatmap, visual-explanation
Last push: 2022-09-17T02:42:00+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": 3750, "days_push": 1446, "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 1668, forks 237 (observed 2026-08-28T04:05:19.827162+00:00)

## What it is
Official Torch (Lua) implementation of Grad-CAM, the ICCV 2017 gradient-weighted class activation mapping technique for producing visual explanations of CNN decisions. It generates heatmap localizations highlighting image regions important for a predicted class, supporting image classification and visual question answering models.

## Use cases
- visualize which image regions a CNN uses for a classification decision
- generate grad-CAM heatmaps for VGG-16, VGG-19, or AlexNet Caffe models
- explain visual question answering model answers with localization maps
- debug CNN failure modes via visual explanations
- produce class-discriminative localization maps without retraining the model
- research interpretability of convolutional neural networks

## When to choose
- you need the reference implementation of the Grad-CAM paper for reproducibility
- you work with legacy Torch/Lua and Caffe CNN models
- you want to explain classification or VQA predictions with gradient-based heatmaps

## When to avoid
- you use PyTorch or TensorFlow - modern ports like pytorch-grad-cam are actively maintained
- you need a license-compliant dependency - this repo has no license
- you want ongoing support or new model architectures - the repo is unmaintained

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing, computer-vision, data-visualization
- domain: deep-learning, computer-vision, machine-learning, image-processing
- platform: lua
- tags: grad-cam, interpretability, explainable-ai, heatmap, visual-explanation, torch, cnn, iccv-2017, vqa, gpu, linux, macos

## Member repositories
- ramprs/grad-cam (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:19.827162+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 2026-08-30T03:42:50.934204+00:00, confidence not recorded.
  - readme: https://github.com/ramprs/grad-cam (fetched 2026-08-28T04:05:19.827162+00:00, sha c414589d6f87)
  - homepage: https://arxiv.org/abs/1610.02391 (fetched 2026-08-29T11:16:11.224496+00:00, sha 4d635b287c3b)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:16:11.228363+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:16:11.231823+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:16:11.233762+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:16:11.230130+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.