Python Deep Learning Cookbook

How to do it...

1. Import the necessary libraries with the following code:

import numpy as npfrom matplotlib import pyplot as pltimport scipy.iofrom keras.models import Sequentialfrom keras.layers.core import Densefrom keras.optimizers import Adam

2. Load the dataset and extract the data we need:

mat = scipy.io.loadmat('./data/train_32x32.mat')mat = mat['X']b, h, d, n = mat.shape

3. Preprocess the data:

# Grayscaleimg_gray = np.zeros(shape =(n, b * h))def rgb2gray(rgb):        return np.dot(rgb[...,:3], [0.299, 0.587, 0.114])for i in range(n):    #Convert to greyscale    img = rgb2gray(mat[:,:,:,i])    img = img.reshape(1, 1024)    img_gray[i,:] = img# NormalizeX_train = img_gray/255.

4. Next, let's define the autoencoder network architecture:

img_size = X_train.shape[1] ...