Python Image Processing Cookbook

Getting ready

First, download the compressed pickled dataset from https://s3-us-west-1.amazonaws.com/udacity-selfdrivingcar/traffic-signs-data.zip. Extract it to the traffic_signs folder inside the images folder (it contains three pickled files, with the images for training, validation, and testing, respectively). Here is the summary of the pickled dataset:

• 34,799 training images
• 4,410 validation images
• 12,630 testing images
• Image size = (32, 32)
• 43 unique classes

Import the following packages to start with:

import pickleimport numpy as npimport pandas as pdimport matplotlib.pylab as pltimport seaborn as snsimport cv2 import torchfrom torch.utils.data.dataset import Datasetfrom torch.utils.data import DataLoaderimport torchvision.transforms ...