Future Work
The following list gives some ideas—in no particular order—for improving
Glimpse in the future.
- The accessibility of the project could be greatly enhanced by integrating
Glimpse into a general machine learning framework. Ideally, this
framework would provide a graphical interface for designing and running
experiments. A good candidate for such a framework is the Orange
project.
- It would be helpful to have more advanced backends, particularly one
targeting GPUs. This could probably be written using PyCUDA or
Theano. Some code for this exists in old versions of the project, and
should be dusted off.
- The biggest boost to accessibility of the project could come from a
graphical user interface, which allows the user to specify arbitrary
network topologies. This might be done by hacking an interface out of the
Orange project’s workbench code.
- Create an app package for OS X, probably using PyInstaller or py2app.
- Create an integrated GUI for running experiments and analyzing results. As
an example, this should integrate the plots shown in the `user guide`_. A
start in this direction has been made using PySide.
- Add an automated loader/downloader for image corpora, similar to the
mechanism provided by scikit-learn. For example, this should allow the
user to download and unpack the AnimalDB dataset with a single command.
- Add a script to perform classification on many sub-windows of the same
image. Use the optimization we built for George’s thesis.
- Add an iterable interface for joblib.Parallel to support a progress meter.