from keras.models import Model from keras.layers import Input, Dense # Define input layer inputs = Input(shape=(10,)) # Define hidden layer x = Dense(units=64, activation='relu')(inputs) # Define output layer outputs = Dense(units=1, activation='sigmoid')(x) # Define model model = Model(inputs=inputs, outputs=outputs)
from keras.optimizers import SGD from keras.losses import binary_crossentropy # Compile model model.compile(optimizer=SGD(lr=0.001), loss=binary_crossentropy, metrics=['accuracy']) # Train model model.fit(x_train, y_train, epochs=10, batch_size=32)
# Evaluate model loss, acc = model.evaluate(x_test, y_test) # Print results print('Test loss:', loss) print('Test accuracy:', acc)This example shows how to evaluate a Keras model using the `evaluate()` method of the `keras.models.Model` class. The method returns the loss and accuracy of the model on the test data. Package library: Keras