The most accessible way to experience modelhub is via modelhub.ai. There you can explore the model collection, try them online, and find instructions on how to run models locally.
But since you are here, follow these steps to get modelhub running on your local computer:
Install Docker (if not already installed)
Follow the official Docker instructions to install Docker CE. Docker is required to run models.
Install Python 2.7 or 3.6 (or higher) (if not already installed)
Download and install Python from the official Python page. Modelhub requires Python 2.7 or Python 3.6 (or higher).
Download modelhub start script
Run a model using start.py
Open a terminal and navigate to the folder that contains start.py. For running models, write access is required in the current folder.
python start.py squeezenetin the terminal to run the squeezenet model from the modelhub collection. This will download all required model files (only if they do not exist yet) and start the model. Follow the instructions given on the terminal to access the web interface to explore the model.
squeezenetby any other model name in the collection to start a different model. To see a list of all available models execute
python start.py -l.
You can also access a jupyter notebook that allows you to experiment with a model by starting a model with the “-e” option, e.g.
python start.py squeezenet -e. Follow the instructions on the terminal to open the notebook.
See additional starting options by executing
python start.py -h.