# keplr-io/quiver

Interactive convnet features visualization for Keras

Repository: https://github.com/keplr-io/quiver
Canonical: https://ross.abutalabs.com/products/keplr-io-quiver
Homepage: https://keplr-io.github.io/quiver/
Language: JavaScript
License: MIT
License Family: permissive
Topics: deep-learning, convolutional-neural-networks, visualization
Last push: 2020-09-04T00:19:41+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": 3580, "days_push": 2190, "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 1784, forks 224 (observed 2026-08-28T04:05:35.893885+00:00)

## What it is
Quiver is a Python library (quiver_engine) that launches an interactive web dashboard to visualize layer activations of Keras convolutional neural network models. It is installed via pip and started with a single line of code, serving a browser-based exploration UI at localhost.

## Use cases
- visualize layer activations of a keras convnet
- inspect what features each cnn layer learns
- debug a keras image classification model interactively
- explore model predictions on a folder of images
- show a deep learning visualization dashboard to students
- understand intermediate convnet feature maps

## When to choose
- you use Keras and want a one-line interactive visualization of convnet activations
- you need a browser dashboard to explore layer outputs on your own images
- you are teaching or demonstrating how CNN layers process images

## When to avoid
- you use PyTorch, TensorFlow 2.x native, or non-Keras models
- you need actively maintained tooling - the project has not been updated since 2020
- you need production model monitoring rather than exploratory visualization

## Facets
- artifact type: library
- maturity: abandoned
- function: data-visualization, deep-learning, machine-learning
- domain: deep-learning, machine-learning, data-visualization, computer-vision
- platform: python, browser
- tags: keras, convnet, activation-visualization, dashboard, interpretability, web-server

## Member repositories
- keplr-io/quiver (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:35.893885+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 2026-08-30T03:24:15.504757+00:00, confidence not recorded.
  - readme: https://github.com/keplr-io/quiver (fetched 2026-08-28T04:05:35.893885+00:00, sha 4c3b4cbc16e3)
  - homepage: https://keplr-io.github.io/quiver/ (fetched 2026-08-29T11:03:01.051154+00:00, sha 5d5ef5bab87b)
- Data as of 2026-08-30T08:39:29.467469+00:00.