How to fix the Keras example in the VS Code documentation?

user_19331835 0
Viewed 80

I've never used Keras or Tensorflow before, and was going through this example in the Visual Studio code documentation, but it seems to have a bug. The documentation shows that their trained model has a 61% accuracy against the test data, which matches what I get when I run it. However, no matter how you modify the neural network parameters, you always get the exact same accuracy. You can even skip the compile and fit commands and still get 61% accuracy.

It turns out that the prediction results they got were all zeroes (which happened to be right 61% of the time against the test data), and no matter how I modify the network it only outputs all zeroes, so it seems like there's some mistake in their code. But since I don't know Keras or TF, I haven't been able to figure out how to make it work.

Here's what I think all the relevant code is, but you can check the link above for everything:

from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(data[['sex','pclass','age','relatives','fare']], data.survived, test_size=0.2, random_state=0)

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(x_train)
X_test = sc.transform(x_test)

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

model = Sequential()

model.add(Dense(5, kernel_initializer = 'uniform', activation = 'relu', input_dim = 5))
model.add(Dense(5, kernel_initializer = 'uniform', activation = 'relu'))
model.add(Dense(1, kernel_initializer = 'uniform', activation = 'sigmoid'))

model.compile(optimizer="adam", loss='binary_crossentropy', metrics=['accuracy'])
model.fit(X_train, y_train, batch_size=32, epochs=50)

y_pred = np.argmax(model.predict(X_test), axis=-1)
print(metrics.accuracy_score(y_test, y_pred))
keras tensorflow python
1 Answers

(as mentioned by @Frightera) np.argmax() is generally used to get max index value when there are more than 2 class probabilities. As it is a binary classification model and you have used Sigmoid activation function in the last layer which always returns the output value between 0 to 1.

Which means

For small values (< 0.5), the output will be classified as zero (0),
and for large values (>0.5), the result will be classified as 1.

Hence, you need to replace the final few lines of your code as below:

preds = model.predict(X_test)
y_pred = np.where(preds > 0.5, 1, 0)
#y_pred = np.argmax(model.predict(X_test), axis=-1)
print(metrics.accuracy_score(y_test, y_pred))

Output:

1.0
user_142906810
Related