-
Notifications
You must be signed in to change notification settings - Fork 369
Comparison
We want to improve CaImAn, this will be done by carefully storing and comparing the results of CaImAn in respect to human defined standards ( labeling of neurons ) and to previous iteration of CaImAn.
In this Regard, any pushed code is going to be tested.
Travis enables to test the code using predefined functions. One of which will be the comparison function Letting master developers possibility to look in the differences whether they are improving or not the present version of CaImAn
It is good to know that you can test the code yourself using the nosetest package
the ground truth is the dataset to which your output result will be compared to.
It is important to know that you shouldn't push new ground truth, you shouldn't tweak the parameters of the function inside of the tests folder without letting a master developer know about it.
If you already know about the fact that your modifications will introduce differences in the output results that leads toward an improvement of CaImAn, you should call the nosetest function and find your comparison results inside the tests/comparison/tests folder. You can then rename the X(number) created folder as "tosend" for it to be sent to the master developers when doing your push request.
It is important to know that more information is present about this in the documentation of the code.
-
A mind map of how the data is stored is present inside the comparison folder.
-
the readme explains how to compare your algorithm
-
look at the function in the tests and comparison folders.
-
Investigative comparison is a notebook being developed to go deeper in the understanding of the differences in the comparison.
You can generate your own ground truth by using the already implemented: create_gt.py function
- select your desired parameters inside the params dictionary of the function
- keep the old ground truth somewhere
- run the function and then you have your new ground truth.