Keras has save and load function in it's api and here is the solution of you question
from keras.models import load_model model.save('my_model.h5') # creates a HDF5 file 'my_model.h5' del model # deletes the existing model # returns a compiled model # identical to the previous one model = load_model('my_model.h5')
You can also save and load only architecture of the model.
# save as JSON json_string = model.to_json() # save as YAML yaml_string = model.to_yaml()
# model reconstruction from JSON: from keras.models import model_from_json model = model_from_json(json_string) # model reconstruction from YAML: from keras.models import model_from_yaml model = model_from_yaml(yaml_string)
Also here is the link you can check out. https://keras.io/getting-started/faq/#how-can-i-save-a-keras-model