Skip to main content

Treescope: An interactive HTML pretty-printer for ML research in IPython notebooks.

Project description

Treescope

Treescope is an interactive HTML pretty-printer and N-dimensional array ("tensor") visualizer, designed for machine learning and neural networks research in IPython notebooks. It's a drop-in replacement for the standard IPython/Colab renderer, and adds support for:

  • Expanding and collapsing subtrees of rendered objects, to let you focus on the parts of your model that you care about,
  • Automatically embedding faceted visualizations of arbitrary-dimensional arrays and tensors directly into the output renderings, so you can quickly understand their shapes and the distribution of their values,
  • Color-coding parts of neural network models to emphasize shared structures,
  • Inserting "copy path" buttons that let you easily copy the path to any part of a rendered object,
  • Customizing the visualization strategy to support rendering your own data structures,
  • And more!

Treescope was originally developed as the pretty-printer for the Penzai neural network library, but it also supports rendering neural networks developed with other libraries, including Equinox, Flax NNX, and PyTorch. You can also use it with basic JAX and Numpy code.

With Treescope, instead of looking at this:

Screenshot of a parameter dictionary without Treescope

You could be looking at this:

Screenshot of a parameter dictionary using Treescope

This is an interactive visualization; try clicking the buttons to expand parts of the output! (You can also hold shift while scrolling to scroll horizontally instead of vertically.)

Documentation on Treescope can be found at https://treescope.readthedocs.io.

Getting Started

You can install Treescope using:

pip install treescope

and import it using:

import treescope

To render a specific object in an IPython notebook with Treescope, you can use treescope.show, which is like print but produces a rich interactive output.

Alternatively, you can simply configure Treescope as the default pretty printer for your notebook via:

treescope.register_as_default()

To turn on automatic array visualization, you can run:

treescope.active_autovisualizer.set_globally(treescope.ArrayAutovisualizer())

Or, if you'd like to both set up Treescope as the default pretty printer and enable automatic array visualization, you can simply run:

treescope.basic_interactive_setup(autovisualize_arrays=True)

Once you've rendered an object, try clicking on it and pressing the r key! This turns on "roundtrip mode", and adds qualified names to every type in the visualization, making it easier to identify what the types in your object are.

For more information on how to use Treescope, check out the Treescope documentation.

Looking for a neural network library with first-class support for Treescope's visualization features? Try Penzai!

Citation

If you have found Treescope to be useful for your research, please consider citing the following writeup (also available on arXiv):

@article{johnson2024penzai,
    author={Daniel D. Johnson},
    title={{Penzai} + {Treescope}: A Toolkit for Interpreting, Visualizing, and Editing Models As Data},
    year={2024},
    journal={ICML 2024 Workshop on Mechanistic Interpretability}
}

This is not an officially supported Google product.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

treescope-0.1.5.tar.gz (405.1 kB view details)

Uploaded Source

Built Distribution

treescope-0.1.5-py3-none-any.whl (174.2 kB view details)

Uploaded Python 3

File details

Details for the file treescope-0.1.5.tar.gz.

File metadata

  • Download URL: treescope-0.1.5.tar.gz
  • Upload date:
  • Size: 405.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.9

File hashes

Hashes for treescope-0.1.5.tar.gz
Algorithm Hash digest
SHA256 75cff86663dfcac133b922fcc0ee9520f605dc9cbedcb34eb86a80476acbbb32
MD5 b17dae38aed080af40a73a07ab5e40cc
BLAKE2b-256 6cecf16cd31702111e1179504bbdf068969a6f6a95e105b48fb16d9ebb3d30a5

See more details on using hashes here.

Provenance

File details

Details for the file treescope-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: treescope-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 174.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.9

File hashes

Hashes for treescope-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 1b07446291212ceafd28e27a26fabcd3299e056307d35f949241991bf190dd65
MD5 f0cc0b3e78fd97ad0ee1d147e7bff0bd
BLAKE2b-256 5a3d8500d47555d5f082b02867e105e646a6677e4c4b7f43c897497929289c3c

See more details on using hashes here.

Provenance

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page