waleedka/hiddenlayer

Health v2 · maintenance only

Adoption not part of the score

1867 stars · 269 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

data-visualization machine-learning deep-learning deep-learning data-visualization machine-learning python cross-platform pytorch tensorflow keras jupyter-notebook neural-network-graphs training-metrics tensorboard-alternative

Member repositories

For agents

markdown · JSON · MCP: product_card(name="waleedka/hiddenlayer")