ivis

Spec sheet

Purpose

ivis is a machine learning library for reducing the dimensionality of very large datasets using Siamese Neural Networks.Read 12 Oct 2026 · beringresearch.github.io

Free plan

YesRead 23 Sep 2026 · beringresearch.github.io

Integrations

The documentation lists callbacks and TensorBoard integration.Read 12 Oct 2026 · beringresearch.github.io

Support

The documentation asks users to report bugs through the GitHub issue tracker and says a reproducible example is helpful.Read 12 Oct 2026 · beringresearch.github.io

License

The GitHub repository identifies its license as Apache-2.0.Read 11 Oct 2026 · github.com

Maker

The repository credits Bering Limited; the maker's site lists its address as 54 Portland Place, London, United Kingdom.Read 11 Oct 2026 · beringresearch.com

Compute options

The Python installation page documents CPU installation and a GPU option for users with CUDA installed.Read 11 Oct 2026 · beringresearch.github.io

Dashboard type

interactiveRead 23 Sep 2026 · beringresearch.github.io

Data inputs

The library supports arbitrary datasets, including N-dimensional arrays, image files on disk, and custom data connectors.Read 12 Oct 2026 · beringresearch.github.io

Dependencies

The Python package documentation lists Python 3.5+, TensorFlow, NumPy, tqdm, and Annoy as dependencies.Read 12 Oct 2026 · beringresearch.github.io

Embeddings

It preserves global data structures in a low-dimensional space and can add new data points to existing embeddings using a parametric mapping function.Read 11 Oct 2026 · beringresearch.github.io

Input data

The documentation lists N-dimensional arrays, image files on disk, and custom data connectors; the repository README also lists NumPy arrays, sparse matrices, and HDF5 files.Read 11 Oct 2026 · beringresearch.github.io

Integration example

A single-cell analysis example uses Scanpy for data import, preprocessing, and normalization before applying ivis.Read 11 Oct 2026 · beringresearch.github.io

Large-data workflow

For out-of-memory training, the docs demonstrate training from HDF5 files and describe custom dataset loaders for other storage, including databases.Read 11 Oct 2026 · beringresearch.github.io

Learning modes

ivis supports unsupervised, semi-supervised, and fully supervised dimensionality reduction.Read 12 Oct 2026 · beringresearch.github.io

New data

A parametric mapping function can add new data points to existing embeddings.Read 12 Oct 2026 · beringresearch.github.io

Platform

webRead 23 Sep 2026 · beringresearch.github.io

Processing

ivis supports in-memory and out-of-memory data processing.Read 12 Oct 2026 · beringresearch.github.io

Python and R

The documentation provides Python and R package sections, and Python installation instructions use pip.Read 11 Oct 2026 · beringresearch.github.io

Python installation

The documentation provides CPU and GPU installation options through pip; the GPU option is for users with CUDA installed.Read 12 Oct 2026 · beringresearch.github.io

Scale

The library states that it scales linearly to millions of observations.Read 12 Oct 2026 · beringresearch.github.io

Structure preservation

The library preserves global data structures in a low-dimensional space.Read 12 Oct 2026 · beringresearch.github.io

Training

Training can be resumed, and the library supports arbitrary neural network backbones.Read 12 Oct 2026 · beringresearch.github.io

Use case

The documentation includes an example applying ivis to visualise single-cell experiments.Read 12 Oct 2026 · beringresearch.github.io

Visualization integration

The project lists callbacks and TensorBoard integration.Read 11 Oct 2026 · beringresearch.github.io

Where Specifiction places it

• Data Visualization Software#86 of 987.2