CODEWITHSUNDEEP
neural-networkkeras
Felix
Felix

Reputation: 23

Keras Sequential Neural Network

I am still learning neural nets and frankly python as well. Here is a basic NN I trained in keras:

from keras.models import Sequential
from keras.layers import Dense
import numpy
# fix random seed for reproducibility
numpy.random.seed(7)

# load pima indians dataset
dataset = numpy.loadtxt("Final_Data.csv", delimiter=",")
# split into input (X) and output (Y) variables
X = dataset[:,0:4]
Y = dataset[:,4]

# create model
model = Sequential()
model.add(Dense(3, input_dim=4, activation='sigmoid'))
model.add(Dense(1, activation='sigmoid'))

# Compile model
model.compile(loss='mean_squared_error', optimizer='sgd', metrics=['accuracy'])


# Fit the model
model.fit(X, Y, epochs=100, batch_size=400)

# evaluate the model
scores = model.evaluate(X, Y)
print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))

If I want to give my own 4 inputs now to see what the neural net outputs, what will the command look like? I think it is the model.predict command but when I give it 4 inputs within the brackets:

model.predict(0.72804878,0.784146341,0.792682927,0.801219512)

I get back:

TypeError: predict() takes at most 4 arguments (5 given)

Now I am guessing I am totally using the predict command wrong, Any suggestions?

Upvotes: 2

Views: 682

Answers (1)

Julio Daniel Reyes
Julio Daniel Reyes

Reputation: 6365

From keras' documentation:

predict(self, x, batch_size=32, verbose=0)

That is why predict is expecting 4 parameters.

The x parameter is what you need to specify correctly.

In your case, x need to be a numpy array of shape (1, 4) that is the number of examples, and the size of each example (the feature vector size).

Try this:

x = np.array([[0.72804878,0.784146341,0.792682927,0.801219512]])
model.predict(x)

Upvotes: 4

Related Questions