Skip to content

Code base for "Generalization in data-driven models of primary visual cortex", Lurz et al. 2020

Notifications You must be signed in to change notification settings

sinzlab/Lurz_2020_code

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

38 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Generalization in data-driven models of primary visual cortex (Code)

Code base for "Generalization in data-driven models of primary visual cortex", Lurz et al. ICLR 2021
Paper: https://openreview.net/forum?id=Tp7kI90Htd
Data: https://gin.g-node.org/cajal/Lurz2020
Video: https://www.youtube.com/watch?v=xwLMO8nVvxs

Requirements

  • docker and docker-compose
  • GIN along with git and git-annex to download the data.

Quickstart

Go to a folder of your choice and type the following commands in a shell of your choice:

git clone https://github.com/sinzlab/Lurz_2020_code.git

# get the data
cd Lurz_2020_code/notebooks/data
gin login
gin get cajal/Lurz2020 # might take a while; fast internet recommended
cd -

# create docker container (possibly you need sudo)
cd Lurz_2020_code/
docker-compose run notebook

Now you should be able to access the jupyter notebooks via YOURCOMPUTER:8888 in the browser. The data you downloaded is the evaluation dataset (Figure 1 in the paper, blue) from the test animal that we tested our transfer cores on in Figure 5. The weights from our best transfer core (11-S in Figure 5, orange line) are stored in Lurz_2020_core/notebooks/models and can be loaded as described in Lurz_2020_core/notebooks/example.ipynb.

If you want to predict your own data with our core, copy your data to the folder Lurz_2020_core/notebooks/data.

About

Code base for "Generalization in data-driven models of primary visual cortex", Lurz et al. 2020

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published