generate images like the stimuli used in visual search experiments
Project description
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.
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
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
Citation
If you use this library, please cite this repository using the DOI:
Acknowledgments
- Research funded by the Lifelong Learning Machines program, DARPA/Microsystems Technology Office, DARPA cooperative agreement HR0011-18-2-0019
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for searchstims-1.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 08707db3bda8522d67c92f38a32e38b6e65f027d01a4cd96009a335c3ed11048 |
|
MD5 | 781213b3a36be1b4e58c3ed07cdbf80c |
|
BLAKE2b-256 | 1ddb41021398277ba8876ab218b04db0fe91521a3a7cd6d72bbe22a434ad4a9f |