Keras architecture visualization#
scikitplot.visualkeras renders Keras/TensorFlow model structure as either a layered architecture diagram or a graph/connectivity diagram. It includes the vendored visualkeras behavior behind the Scikit-Plots namespace.
Important
Visualization is derived from model metadata and framework internals. Test representative models against the exact Keras/TensorFlow version you ship; a rendered diagram is not a validation of model computation or tensor correctness.
Render a Keras model with layered_view or graph_view.
Dimension scaling, ignored layers, text, spacing, colors, and CNN-style diagrams.
Connectivity-oriented visualization for functional/branched models.
Color maps, labels, SpacingDummyLayer, image output, and layout trade-offs.
The three stable top-level exports and dependency behavior.
TensorFlow/Keras/Pillow/aggdraw optionality, model-shape caveats, and current maintenance findings.
Unsupported layer shapes, Keras-version differences, fonts/output files, and large diagrams.
Which page should I use?#
Start with Getting started. Then choose the page that owns the decision you are making: architecture and lifecycle, configuration, persistence, performance, public API, or limits. The guide intentionally separates those concerns so examples do not accidentally become policy.
Examples#
See Visualkeras for executable examples that accompany this guide.
Further reading#
See also