ivis: dimensionality reduction in very large datasets using Siamese Networks

Major ivis release!

Version 2.0 features:

• Unsupervised, semi-supervised, and fully supervised dimensionality reduction
• Support for arbitrary datasets:
  • N-dimensional arrays
  • Image files on disk
  • Custom data connectors
• In- and out-of-memory data ingestion
• Resumable training
• Arbitrary neural network backbones
• Customizable neighbour retrieval
• Callbacks and Tensorboard integration

ivis: dimensionality reduction in very large datasets using Siamese Networks

• Added support for TensorFlow 2.3.0
• Visualise embeddings using EmbeddingsExplorer class through datashader in Jupyter notebooks

ivis: dimensionality reduction in very large datasets using Siamese Networks

Improved handling of n-dimensional arrays and HDF5 files

ivis: dimensionality reduction in very large datasets using Siamese Networks

Support for dimensionality reduction of arbitrary n-dimensional arrays.

ivis: dimensionality reduction in very large datasets using Siamese Networks

Compatibility fixes with tensorflow ≥1.13.1

ivis: dimensionality reduction in very large datasets using Siamese Networks

• Introducing neighbour_matrix parameter for provision of arbitrary KNNs.
• Transition to tf.Datasets, improving memory efficiency and overall stability

ivis: dimensionality reduction in very large datasets using Siamese Networks

1.7.2

Merge pull request #64 from beringresearch/revert-63-keras-sequence-t…

ivis: dimensionality reduction in very large datasets using Siamese Networks

This release addresses #50 by making it easy to alternate between CPU- and GPU-enabled tensor flow backend

ivis: dimensionality reduction in very large datasets using Siamese Networks

Major features:

• Support for semi-supervised dimensionality reduction
• Switch from using fit_generator to fit for training the Keras model
• Address eager execution issues with TF 2.0
• User-configurable on-disk-building of Annoy index.
• Tidy handling of interrupted multi-thread processes

Minor features:

• Tests for semi-supervised DR

• Improved input validation

• Better hyper parameter validation

• Slight changes to default hyperparameters

• Bug fixes

ivis: dimensionality reduction in very large datasets using Siamese Networks

• Control eager execution
• R package updates and improvements
• Save ivis object with a custom model
• Bug squashes and performance improvements