If you like what you see here, please post this website on other sites. Message me directly on Twitter with any comments.

Using a confusion matrix within Keras

27 May 2019

Assuming that y_label are the actual gold standard labels that you want to evaluate, you can use sklearn’s confusion matrix function in order to evaluate a keras model.

Code would look like the following

import numpy as np
from sklearn.metrics import confusion_matrix

model = <use your favorite keras model here> 

y_pred = model.predict(test_data, test_labels)
y_pred_max = np.apply_along_axis(lambda x : np.argmax(x) +1, axis =1, arr=y_pred)
cm = confusion_matrix(test_label, y_pred_max)