1 repository
Methods to reduce the number of trainable parameters by using linear approximations of convolutions.
Distinguishing note: The candidates refer to database map-reduces or statistical parameter estimation, not architectural parameter reduction.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Parameter Reduction Techniques. Refine with filters or upvote what's useful.
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
Provides logic to generate feature maps using a small number of expensive convolutions and cheap linear operations.