Ross ROSS = Recommend OSS · open-source software intelligence for agents

gwding/draw_convnet

None observed · 2026-08-28

github.com/gwding/draw_convnet · Python observed · 2026-08-28

Health v2 · maintenance only

32/100

  • Activity 0
  • Release rhythm 35
  • Longevity 100

Flags: no_releases no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 3843
  • days_rel: n/a
  • days_push: 802
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

2860 stars · 519 forks observed · 2026-08-28

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

A Python script that generates illustrations of Convolutional Neural Network (ConvNet) architectures using matplotlib. It produces publication-quality figures showing network layers and feature channels, useful for papers and teaching.

Use cases

  • draw a convolutional neural network diagram for a paper
  • visualize convnet architecture layers
  • generate CNN figures for teaching materials
  • create neural network illustrations with matplotlib
  • make a convnet figure with omitted channels

When to choose

  • you need a static ConvNet architecture figure for a paper or slides
  • you want a simple, dependency-light matplotlib-based drawing script

When to avoid

  • you need interactive or web-based neural network visualization
  • you want to visualize live training or real model weights
  • you need diagrams of architectures beyond convolutional networks

Facets

library · maturity maintenance

data-visualization deep-learning deep-learning data-visualization education python convnet diagram-generation matplotlib educational-figures neural-network-visualization

1 source

Member repositories

RepositoryRoleHealth v2
gwding/draw_convnetmain32

For agents

markdown · JSON · MCP: product_card(name="gwding/draw_convnet")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem