This project was created using whisk. whisk creates a logical and flexible project structure for ML with reproducible results and lets you release your model to the world without becoming a software engineer.
The following is required to run this project:
- Git (configured with a user name and email)
- Python 3.6+
- A Linux-based OS (includes OSX)
After cloning this repo and cd bike_image_classifier_tensorflow
:
- If you haven't yet installed whisk, run
pip install whisk
- Run
whisk setup
. The install script creates avenv
, installs the Python dependencies specified, and initializes DVC. - Activate the venv:
source venv/bin/activate
- If DVC is used, Download the latest data files:
dvc pull
.
To learn more about whisk, here are a few helpful doc pages:
After running the setup, you an invoke the model from the command line. We have a few bike examples hosted for testing:
$ bike_image_classifier predict [\"https://whisk-examples.s3.amazonaws.com/bike-images/mountain_bike.jpg\"]
Mountain: 0.9900122, Road: 0.009987746
$ bike_image_classifier predict [\"https://whisk-examples.s3.amazonaws.com/bike-images/road_bike.jpg\"]
Mountain: 0.12031126, Road: 0.87968874
Project built with the whisk ML project framework based on the cookiecutter data science project template. #cookiecutterdatascience