torchkit is a lightweight library containing PyTorch utilities useful for day-to-day research. Its main goal is to abstract away a lot of the redundant boilerplate associated with research projects like experimental configurations

A general framework for inferring CNNs efficiently. Reduce the inference latency of MobileNet-V3 by 20% on an iPhone XS Max without sacrificing accuracy.

A Bayesian optimization toolbox built on TensorFlow. Trieste is named after the bathyscaphe Trieste, the first vehicle to take a crew to Challenger Deep in the Mariana Trench, the lowest point on the Earth's surface: the literal g

The official implementation of the paper "PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction" by Eli Simhayev, Gilad Katz and Lior Rokach.

An implementation of Performer, a linear attention-based transformer variant with a Fast Attention Via positive Orthogonal Random features approach (FAVOR+).

An implementation of Linformer in Pytorch. Linformer comes with two deficiencies. (1) It does not work for the auto-regressive case. (2) Assumes a fixed sequence length.

Unofficial Pytorch code for "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence" in NeurIPS'20. This repo contains reproduced checkpoints.