Python Deep Learning Cookbook

How to do it...

1. Load the libraries with the following code:

import numpy as npfrom matplotlib import pyplot as pltfrom sklearn.metrics import confusion_matrixfrom keras.datasets import mnistfrom keras.models import Sequentialfrom keras.layers import Dense, Dropoutfrom keras.optimizers import Adamfrom keras.callbacks import EarlyStopping

2. Import the MNIST dataset and create an imbalanced dataset with 9s and 4s:

(X_train, y_train), (X_test, y_test) = mnist.load_data()# Extract all 9s and 100 examples of 4sy_train_9 = y_train[y_train == 9]y_train_4 = y_train[y_train == 4][:100]X_train_9 = X_train[y_train == 9]X_train_4 = X_train[y_train == 4][:100]X_train = np.concatenate((X_train_9, X_train_4), axis=0)y_train = np.concatenate((y_train_9, ...