1. Learn
    2. /
  2. Courses
    3. /
  3. Image Modeling with Keras
Connected

Exercise

Evaluating a classifier

To evaluate a classifier, we need to test it on images that were not used during training. This is called "cross-validation": a prediction of the class (e.g., t-shirt, dress or shoe) is made from each of the test images, and these predictions are compared with the true labels of these images.

The results of cross-validation are provided as one-hot encoded arrays: test_labels and predictions.

Instructions

100 XP
  • Multiply the arrays with each other and sum the result to find the total number of correct predictions.
  • Divide the number of correct answers (the sum) by the length of predictions array to calculate the proportion of correct predictions.