Running models¶
With the virtual environment activated, there are two ways to run models
through neon. The first is to simply execute the python script
containing the model (with -b mkl
), as mentioned before:
examples/mnist_mlp.py # equivalent to examples/mnist_mlp.py -b mkl
This will run the multilayer perceptron (MLP) model and print the final
misclassification error after 10 training epochs. On the first run, neon will download the MNIST dataset. It will create a ~/nervana
directory where the raw datasets are kept. The data directory can be controlled with the -w
flag.
The second method is to specify the model in a YAML file.
YAML is a widely-used markup language. For
examples, see the YAML files in the examples
folder. To run the YAML
file for the MLP example, enter from the neon repository directory:
neon examples/mnist_mlp.yaml
In a YAML file, the mkl backend can be specified by adding backend: mkl
.
Arguments¶
Both methods accept command line arguments to configure how you would
like to run the model. For a full list, type neon --help
in the
command line. Some commonly used flags include: