How to save keras models?

Recipe Objective

How to save a Keras Model. To Learn How to Save model, We will create a sample model, then we will save it.

Step 1- Import Libraries.

from keras.models import Sequential from keras.layers import Dense from keras.models import model_from_json import numpy

Step 2- Creating Neural Network Model.

We will create neural network model with necessary parameters and compile it.

# create model model = Sequential() model.add(Dense(12, input_dim=8, activation='relu')) model.add(Dense(8, activation='relu')) model.add(Dense(1, activation='sigmoid')) # Compile model model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

Step 3- Save the model.

Before saving your Model do not forget to create an empty folder in your local system or google drive. model.save('your_location')

Step 4- Converting to JSON

We can convert our model to a JSON file as well. model_json = model.to_json()

Step 5- Saving our Weights.

model.save_weights("model.h5")