# waleedka/hiddenlayer

Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.

Repository: https://github.com/waleedka/hiddenlayer
Canonical: https://ross.abutalabs.com/products/hiddenlayer
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, tensorflow, deeplearning, visualization, keras, tensorboard
Last push: 2024-02-11T12:41:49+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": 3029, "days_push": 934, "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 1867, forks 269 (observed 2026-08-28T04:05:46.325086+00:00)

## What it is
A lightweight Python library for rendering readable neural network architecture graphs and plotting training metrics for PyTorch, TensorFlow, and Keras models. It works well in Jupyter Notebook and is designed to be simple and easily hackable, not a replacement for TensorBoard.

## Use cases
- visualize neural network architecture as a graph in jupyter
- plot training loss and accuracy curves in a notebook
- render model graph to png or pdf
- fold common layer sequences into simplified graph blocks
- monitor training metrics from a headless server by saving snapshots

## When to choose
- you want quick, readable model architecture diagrams without heavyweight tooling
- you train models in Jupyter Notebook and want inline metric plots
- you need a small, hackable visualization library you can extend

## When to avoid
- you need full-featured experiment tracking like TensorBoard or Weights & Biases
- you need production-grade dashboards or remote metric logging
- you need actively developed features - the project sees only occasional maintenance

## Facets
- artifact type: library
- maturity: maintenance
- function: data-visualization, machine-learning, deep-learning
- domain: deep-learning, data-visualization, machine-learning
- platform: python, cross-platform
- tags: pytorch, tensorflow, keras, jupyter-notebook, neural-network-graphs, training-metrics, tensorboard-alternative

## Member repositories
- waleedka/hiddenlayer (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:46.325086+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 2026-08-30T03:15:31.445154+00:00, confidence not recorded.
  - readme: https://github.com/waleedka/hiddenlayer (fetched 2026-08-28T04:05:46.325086+00:00, sha 7f1e61fe8967)
  - registry_pypi: https://pypi.org/pypi/hiddenlayer/json (fetched 2026-08-29T10:54:33.274192+00:00, sha 67cb435fa902)
- Data as of 2026-08-30T08:39:29.467469+00:00.