Deep Learning By Example

Data analysis and preprocessing

We need to analyze the dataset and do some basic preprocessing. So, let's start off by defining some helper functions that will enable us to load a specific batch from the five batches that we have and print some analysis about this batch and its samples:

# Defining a helper function for loading a batch of imagesdef load_batch(cifar10_dataset_dir_path, batch_num):        with open(cifar10_dataset_dir_path + '/data_batch_' + str(batch_num), mode='rb') as file:        batch = pickle.load(file, encoding='latin1')    input_features = batch['data'].reshape((len(batch['data']), 3, 32, 32)).transpose(0, 2, 3, 1)    target_labels = batch['labels']    return input_features, target_labels

Then, we define a function that can help us display ...