Skip to main content

generate images like the stimuli used in visual search experiments

Project description

Build Status License DOI PyPI version

searchstims

Python package to make stimuli like those used in classic visual search experiments
https://en.wikipedia.org/wiki/Visual_search
... but with the exact size to feed them to your favorite neural network.

feature_search spatial_config_search

There are links to example configuration files below.

For a recent review of factors influencing visual search, please see:
http://search.bwh.harvard.edu/new/pubs/FiveFactors_Wolfe-Horowitz_2017.pdf

For a dataset of human subjects performing a similar visual search task, please see: http://search.bwh.harvard.edu/new/data_set_files.html

Installation

pip install searchstims

If you want to download and install locally into an environment with Anaconda: /home/you/Documents $ conda create -n searchstims-env python=3.6 numpy pygame
/home/you/Documents $ source activate searchstims-env
(searchstims-env) /home/you/Documents $ git clone
(searchstim) /home/you/Documents $ cd searchstims
(searchstim) /home/you/Documents/searchstims $ pip install -e .

Usage

The searchstims package installs itself so that you can run it from the command line. You will use a config.ini file to specify the visual search stimuli you want the package to generate.

/home/you/Documents $ searchstims config.ini

Running the example script will create a folder ~/output with visual search stimuli. For more detail on the structure of config.ini files used with this package, see ./doc/config.md.

For examples of config.ini files, see ./doc/configs/. These examples were used in this project:
https://github.com/NickleDave/visual-search-nets

.json output file

In addition to saving visual search stimuli in the output folder, searchstims saves information about stimuli in a .json output file. This .json file is provided to make it easier to work with the visual search image files, and analyze results obtained with them. For more detail, see ./doc/json.md

License

BSD-3

Citation

If you use this library, please cite this repository using the DOI:
DOI

Acknowledgments

  • Research funded by the Lifelong Learning Machines program, DARPA/Microsystems Technology Office, DARPA cooperative agreement HR0011-18-2-0019

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

searchstims-2.0.0.tar.gz (16.2 kB view hashes)

Uploaded Source

Built Distribution

searchstims-2.0.0-py3-none-any.whl (21.0 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page