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).
Questo esercizio fa parte del corso
Image Modeling with Keras
Istruzioni dell'esercizio
- Load the weights from a file called
'weights.hdf5'. - Predict the classes of the first three images from
test_data.
Esercizio pratico interattivo
Prova a risolvere questo esercizio completando il codice di esempio.
# Load the weights from file
model.____
# Predict from the first three images in the test data
____