skip to navigation
skip to content

Not Logged In

glimpse 0.1.0

Library for hierarchical visual models in C++ and Python

Package Documentation

Latest Version: 0.2.1

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.

[1]S. Brumby, G. Kenyon, W. Landecker, C. Rasmussen, S. Swaminarayan, and L. Bettencourt, "Large-Scale Functional Models of Visual Cortex for Remote Sensing," in Applied Imagery Pattern Recognition 2009 (AIPR ’09), 2009.
 
File Type Py Version Uploaded on Size
glimpse-0.1.0.tar.gz (md5) Source 2012-05-08 209KB
  • Downloads (All Versions):
  • 19 downloads in the last day
  • 65 downloads in the last week
  • 435 downloads in the last month