To see OpenCL-based Random Forest Classifiers in action, check out the demo-notebook. For optimal performance and classification quality, it is recommended to generate feature stacks that fit well to the the image data you would like to process.
You can install oclrfc
via [pip]. Note: you also need pyopencl.
conda install pyopencl
pip install oclrfc
Contributions are very welcome. Tests can be run with [tox], please ensure the coverage at least stays the same before you submit a pull request.
Distributed under the terms of the BSD-3 license, "oclrfc" is free and open source software
If you encounter any problems, please open a thread on image.sc along with a detailed description and tag @haesleinhuepf.