All Versions
7
Latest Version
Avg Release Cycle
134 days
Latest Release
2014 days ago

Changelog History

  • v0.1.6 Changes

    September 08, 2019

    ⚡️ Update to PyTorch v1.1.0.

  • v0.1.5

    May 20, 2018

  • v0.1.4

    February 18, 2018

  • v0.1.3 Changes

    December 14, 2017

    v0.1.3 (2017-12-14)

    ➕ Added

    • Goodbooks dataset.

    🔄 Changed

    • Raise ValueError if loss becomes NaN or 0.
    • ⚡️ Updated to work with PyTorch 0.3.0.

  • v0.1.2 Changes

    September 19, 2017

    ➕ Added

    • spotlight.layers.BloomEmbedding: bloom embedding layers that reduce the number of
      🛠 parameters required by hashing embedding indices into some fixed smaller dimensionality,
      following Serrà, Joan, and Alexandros Karatzoglou. "Getting deep recommenders fit: Bloom
      📜 embeddings for sparse binary input/output networks."
    • sequence_mrr_score now accepts an option that excludes previously seen items from scoring.

    🔄 Changed

    • ⚡️ optimizer arguments is now optimizer_func. It accepts a function that takes a single argument (list of model parameters) and return a PyTorch optimizer (thanks to Ethan Rosenthal).
    • fit calls will resume from previous model state when called repeatedly (Ethan Rosenthal).
    • ⚡️ Updated to work with PyTorch v0.2.0.

    🛠 Fixed

    • 📚 Factorization predict APIs now work as advertised in the documentation.

  • v0.1.1

    July 19, 2017

  • v0.1.0

    June 28, 2017