Write a convolutional network in Keras to train the Mini-ImageNet 
dataset on the course website. Your constraint is to create a network
that achieves at least 70% test accuracy.

Submit your assignments as two files train.py and test.py. Make
train.py take three inputs: the input training data, training labels,
and a model file name to save the model to. 

python train.py <train.npy> <trainlablels.npy> <model file>

It is straightforward to save a Keras model to file, see the simple example here 
https://keras.io/getting-started/faq/#savingloading-whole-models-architecture-weights-optimizer-state

Make test.py take three inputs: the input test data, test labels,
and a model file name to load the model. 

python test.py <test.npy> <testlabels.npy> <model file>

The output of test.py is the test error of the data which is
the number of misclassifications divided by size of the test set.

Copy both your programs and model file to your AFS 
course folder /afs/cad/courses/ccs/s19/cs/677/002/<UCID>. The 
assignment is due on April 12th 2019.