Python Image Processing Cookbook

How to do it...

Go through the following the steps for training a deep neural net on the GTSRB images for traffic sign classification:

1. Load the pickle files corresponding to the training, validation, and test datasets:

training_file = "traffic_signs/train.p"validation_file = "traffic_signs/valid.p"testing_file = "traffic_signs/test.p"with open(training_file, mode='rb') as f: train = pickle.load(f)with open(validation_file, mode='rb') as f: valid = pickle.load(f)with open(testing_file, mode='rb') as f: test = pickle.load(f)

2. Extract the features (the images) and the labels (the traffic signs) from the training, validation, and test images using the following code snippet:

X_train, y_train = train['features'], train['labels']X_valid, y_valid ...