Library for hierarchical visual models in C++ and Python
Project description
The GLIMPSE project is a library for implementing hierarchical visual models in C++ and Python. The goal of this project is to allow a broad range of feed-forward, hierarchical models to be encoded in a high-level declarative manner, with low-level details of the implementation hidden from view. GLIMPSE combines an efficient implementation with the ability to leverage parallel processing facilities and is designed to run on multiple operating systems using only common, freely-available components. A prototype of GLIMPSE has been used to encode an HMAX-like model, achieving results comparable with those found in the literature.
The GLIMPSE library began as a port of the Petascale Artificial Neural Network project [1], and owes a great deal to that work. Additionally, we acknowledge NSF Grant 1018967 (PIs: Melanie Mitchell and Garrett Kenyon) for support.
See also the documentation and the GitHub code repository.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.