Python Deep Learning Cookbook

How to do it...

1. Import all necessary libraries:

import numpy as npfrom matplotlib import pyplot as pltfrom keras.utils import np_utilsfrom keras.models import Sequentialfrom keras.layers.core import Dense, Dropout, Activation, Flattenfrom keras.callbacks import EarlyStoppingfrom keras.layers import Conv2D, MaxPooling2Dfrom keras.layers.normalization import BatchNormalization

2. Load the cifar10 dataset:

from keras.datasets import cifar10(X_train, y_train), (X_val, y_val) = cifar10.load_data()

3. Normalize the input data:

X_train = X_train.astype('float32')/255.X_val = X_val.astype('float32')/255.

4. One-hot encode the labels:

n_classes = 10y_train = np_utils.to_categorical(y_train, n_classes)y_val = np_utils.to_categorical(y_val, n_classes) ...