Authors: Mehdi Cherti & Balazs Kegl

Go to ramp-worflow for more help on the RAMP ecosystem.

After cloning, run

python download_data.py

the first time. It will create data/imgs and download the images there using the names <id>, where <id>s are coming from data/train.csv and data/test.csv. If images are properly unzipped in data/imgs, you can delete the zip file data/imgs.zip to save space.

You should install keras 2.0.6, for example, like this:

conda install -c conda-forge keras

You should install keras and set image_data_format to channels_first in ~/.keras/keras.json.

Install ramp-workflow (rampwf), then execute

ramp_test_submission

Get started on this RAMP with the dedicated notebook.