Exercise

Using stored weights to predict in a test set

Model weights stored in an hdf5 file can be reused to populate an untrained model. Once the weights are loaded into this model, it behaves just like a model that has been trained to reach these weights. For example, you can use this model to make predictions from an unseen data set (e.g. test_data).

Instructions

100 XP

Load the weights from a file called 'weights.hdf5'.
Predict the classes of the first three images from test_data.