Here we used PyTorch to train a convolutional neural network (CNN) based image classifier using CIFAR-10 dataset to train and evaluate the model. We should try different values for the CNN hyper-parameters and study the effect of each of them on the model performance.
CIFAR-10 Dataset
The CIFAR-10 dataset consists of 60,000 32x32 colour images in 10 classes, with 6000 images
per class. The classes are completely mutually exclusive.
There is no overlap between automobiles and trucks. ”Automobile” includes sedans, SUVs, things of that sort. ”Truck” includes
only big trucks. Neither includes pickup trucks.
You can download the dataset from here.
Here are the classes in the dataset, as well as 10 random images from each:
