Pinned Loading

1. imbalanced-losses imbalanced-losses Public

   imbalanced-losses is a PyTorch library of training losses for class-imbalanced classification — including Focal Loss, Smooth-AP, and Recall-at-Quantile — with built-in DDP all-gather support for gl…

   Python

2. ml-lab ml-lab Public

   Claude Code agent for rigorous ML hypothesis investigation: critic-defender debate (default) or ensemble critique (opt-in), pre-specified metrics, agreed empirical tests, and production re-evaluati…

   Python

3. vime vime Public

   Reproducing the VIME framework for self- and semi-supervised learning to tabular domain.

   Python 4

4. met met Public

   Reproducing the MET framework with PyTorch

   Python 5 1

5. steps steps Public

   A SciKit-Learn style feature selector using best subsets and stepwise regression.

   Jupyter Notebook 5

6. ferrum ferrum Public

   Ferrum is a statistical visualization library for Python: a grammar-first charting system that unifies exploratory plots, statistical graphics, interactive views, and model diagnostics, backed by a…

   HTML