how does prediction with keras work?

Question

so, I've been racking my head over the following code. please help me.

# first neural network with keras tutorial
from numpy import loadtxt
from keras.models import Sequential
from keras.layers import Dense
# load the dataset
dataset = loadtxt('pima-indians-diabetes.csv', delimiter=',')
# split into input (X) and output (y) variables
X = dataset[:,0:8]
y = dataset[:,8]
# define the keras 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 the keras model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit the keras model on the dataset
model.fit(X, y, epochs=150, batch_size=10)
# evaluate the keras model
accuracy = model.evaluate(X, y)
print('Accuracy: %.2f' % (accuracy*100))

any help would be greatly appreciated. thank you!

Answer 1

U want to learn keras posted in Sololearn ? )
So.
Firstly, u import modules, as usual.
Than u load dataset in csv format.
Than u split dataset X and y.
Make an instance of model.
model.add - u have 3 layers in your model with activation function relu and sigmoid ( strange thing to use different functions at the same tume).
Than u compile model, using binary_ crossentropy, that say u will have on exit only 2 variants of answer.
Than u fit model on your splitted dataset. U use 150 epoch, not much but enough.
And finally, u evaluate a model and find out the accuracy of a model.

Answer 2

@zoldaten, thanks, but can you tell me more about model.add?