Image classification using PyTorch with DenseNet a type of CNN network.
-
In this study, the CIFAR100 dataset, one of the ready-made datasets in the torchvision library, was used.
-
The CIFAR-100 dataset consists of 60,000 color images of 100 different classes. Each class contains 600 images, of which 500 are reserved for training and 100 for testing. The images are 32x32 pixels in size and represent various objects (e.g. airplanes, cars, birds, cats).