# raghakot/keras-vis

Neural network visualization toolkit for keras

Repository: https://github.com/raghakot/keras-vis
Canonical: https://ross.abutalabs.com/products/keras-vis
Homepage: https://raghakot.github.io/keras-vis
Language: Python
License: MIT
License Family: permissive
Topics: visualization, keras, deep-learning, theano, tensorflow, neural-networks, machine-learning
Last push: 2022-02-07T16:06:07+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3582, "days_push": 1668, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2991, forks 635 (observed 2026-08-28T04:07:35.328172+00:00)

## What it is
keras-vis is a high-level Python toolkit for visualizing and debugging trained Keras neural network models. It supports activation maximization, saliency maps, and class activation maps, framed as energy minimization problems with an extensible loss/regularizer interface.

## Use cases
- visualize what features a keras CNN layer has learned
- generate saliency maps to explain model predictions
- compute class activation maps for image classifiers
- debug a trained neural network by inspecting activations
- generate images that maximally activate a filter
- understand why a keras image model misclassifies

## When to choose
- you maintain a legacy Keras (or Theano/TensorFlow 1.x backend) model and need activation maximization, saliency, or CAM visualizations
- you want a simple, extensible loss/regularizer interface for image backprop experiments

## When to avoid
- you use modern TensorFlow 2.x / tf.keras or PyTorch - the project is unmaintained and incompatible with current versions
- you need actively supported interpretability tooling - prefer alternatives like tf-keras-vis, Grad-CAM libraries, or Captum
- you need non-image modality visualizations

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, data-visualization, deep-learning
- domain: deep-learning, machine-learning, data-visualization
- platform: python
- tags: keras, neural-networks, saliency-maps, activation-maximization, class-activation-maps, model-interpretability, explainability

## Member repositories
- raghakot/keras-vis (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:35.328172+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 2026-08-29T18:47:26.968511+00:00, confidence not recorded.
  - readme: https://github.com/raghakot/keras-vis (fetched 2026-08-28T04:07:35.328172+00:00, sha dfbb0001f83c)
  - homepage: https://raghakot.github.io/keras-vis (fetched 2026-08-29T09:46:16.037576+00:00, sha 08a881357904)
  - registry_pypi: https://pypi.org/pypi/keras-vis/json (fetched 2026-08-29T09:46:16.040057+00:00, sha ab3bfd5dc6f7)
- Data as of 2026-08-30T08:39:29.467469+00:00.