Showing 3 of 3 projects
A scikit-learn-compatible Python implementation of ReBATE, a suite of Relief-based feature selection algorithms for machine learning.
A TensorFlow implementation of Dynamic Capacity Networks, which reduces computations by applying high-capacity networks to selected input patches.
A dynamic inference wrapper for Transformer language models that enables per-token layer skipping to reduce computational FLOPs.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.