This repository provides a PyTorch implementation of LambdaNetworks, a new approach to image recognition that achieves state-of-the-art performance on ImageNet with reduced computational cost. The core innovation is the lambda layer, which captures interactions between inputs and context by transforming contexts into linear functions (lambdas) and applying them to each input element. The implementation supports both global and localized context variants, and includes both PyTorch and TensorFlow/Keras versions.