v1s eval for MIT 6.870 (2009)
License
npinto/v1s-0.0.4_scene
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
=============================================================================== V1S 0.0.4 -- Basic V1-Like (simple cells) Object Recognition System ------------------------------------------------------------------------------- Nicolas Pinto (pinto@mit.edu) David Cox (davidcox@mit.edu) James DiCarlo (dicarlo@mit.edu) ------------------------------------------------------------------------------- This code has been used in the following research articles: Why is Real-World Visual Object Recognition Hard? (2008) Pinto N, Cox DD, DiCarlo JJ PLoS Computational Biology Vol. 4, No. 1, e27 doi:10.1371/journal.pcbi.0040027 Establishing Good Benchmarks and Baselines for Face Recognition (2008) Pinto N, Dicarlo JJ, Cox DD ECCV 2008 Faces in 'Real-Life' Images Workshop. ------------------------------------------------------------------------------- Copyright 2008 - DiCarlo Lab at MIT and MIT All rights reserved. Permission to copy and modify this data, software, and its documentation only for internal research use in your organization is hereby granted, provided that this notice is retained thereon and on all copies. This data and software should not be distributed to anyone outside of your organization without explicit written authorization by the authors and MIT. It should not be used for commercial purposes without specific permission from the authors and MIT. MIT also requires written authorization by the authors to publish results obtained with the data or software and possibly citation of relevant reference papers. We make no representation as to the suitability and operability of this data or software for any purpose. It is provided "as is" without express or implied warranty. =============================================================================== This set of python scripts have successfuly been tested under GNU/Linux and Mac OS X. You will need the following open source python libaries: - numpy (tested with version 1.0.1) - scipy (tested with version 0.5.2) - PyML (tested with version 0.6.11 and 0.7.0) - Python Imaging Library (tested with version 1.1.5) ------------------------------------------------------------------------------- Example of use: # Download Caltech 101 Dataset wget http://www.vision.caltech.edu/Image_Datasets/Caltech101/\ 101_ObjectCategories.tar.gz # Extract archive content tar xzvf 101_ObjectCategories.tar.gz -C /tmp # Assess the performance of a simple V1-like model python ./v1s_run.py params_simple.py /tmp/101_ObjectCategories # Assess the performance of a simple V1-like model + cheap tricks python ./v1s_run.py params_simple_plus.py /tmp/101_ObjectCategories ------------------------------------------------------------------------------- Known Issue: Note that you may need a lot of memory to run the program. A MemoryError exception will be raised if your operating system can't allocate enough memory (remember that one process cannot address more than 4GB on a 32bit system). -------------------------------------------------------------------------------
About
v1s eval for MIT 6.870 (2009)
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published