PlugNPlay-Modules is a collection of reusable PyTorch computer vision modules and deep learning architectural components. It provides a library of standardized building blocks for constructing neural networks, focusing on attention mechanisms, signal processing layers, and feature fusion modules.
The project is distinguished by its extensive variety of attention primitives, covering spatial, channel, and temporal weighting, as well as specialized variants like deformable, frequency-enhanced, and linear-complexity attention. It also implements advanced signal processing tools within the neural network context, including discrete wavelet transforms, Laplacian pyramid decomposition, and frequency-domain filtering.
The codebase covers a broad surface of capabilities, including multi-scale feature extraction, hierarchical feature fusion, and various convolutional layer optimizations. It further includes utilities for tensor normalization, contrastive learning, and specialized loss functions for imbalanced datasets.
