Сifar10

The CIFAR-10 dataset consists of 60000 32x32 color images divided into 10 classes, each with 6000 images. Each image belongs to one of ten categories: airplane, car, bird, cat, deer, dog, frog, horse, ship, or truck. This dataset is often used to test and compare different machine learning algorithms in computer vision and image processing.

names_classes = ['airplane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']

As part of the training process, Xception (Extreme Inception) was used to train cifar-10, which is a deep neural network for image classification, which was proposed by Francois Chollet in 2016.

With summary() - you can see the general structure of the model, including the number of layers and their dimensions, the number of parameters, and the number of input and output tensors.

In the Keras machine learning model, layers are the basic building block of the model. Each layer takes input data, performs predefined operations on that data, and returns output data.

evaluate() - is a method used to evaluate the accuracy of a machine learning model. It takes input data for evaluation and returns evaluation metrics: loss, accuracy.

Graphs for building model performance

The Confusion Matrix is ​​a table used to evaluate the effectiveness of a machine learning model in classification tasks. Each row of the table corresponds to an actual class label, and each column corresponds to a predicted class label. The element in row i and column j shows the number of decrees when the model correctly classified examples from class i as class j (true positive), or incorrectly classified an example from class i as class j (false positive).