The MNIST xe "convnet (convolutional neural network)"convnet's prediction for each MNIST digit will be an array of 10 probabilities, indicating the likelihood that the digit belongs to a particular one of the classes 0 through 9. When we evaluate the model's accuracy, Keras compares the model's predictions to the dataset's labels. To do that, Keras requires both to have the same ________.
A) profile
B) aspect
C) shape
D) frame

Question

Quizplus · Accepted Answer

In order to compare the model's predictions to the dataset's labels, they must have the same shape, meaning the same number of dimensions and number of elements along each dimension. The other options (profile, aspect, frame) do not accurately describe the required similarity between the predictions and labels.

The MNIST Xe "Convnet (Convolutional Neural Network)"convnet's Prediction for Each