autoencoder_with_img.py

import pickle
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

def unpickle(file):
    fo = open(file, 'rb')
    dict = pickle.load(fo)
    fo.close()
    return dict

def grayscale(a):
    return a.reshape(a.shape[0], 3, 32, 32).mean(1).reshape(a.shape[0], -1)

def data_show(data, data_len):
    plt.rcParams['figure.figsize'] = (2, 2)
    for i in range(data_len):
        img = np.reshape(data[i,:], (32, 32))
        plt.subplot(1, data_len, i+1)
        plt.imshow(img, cmap='gray')
        
names = unpickle('./cifar-10-batches-py/batches.meta')['label_names']

data, labels = [], []
for i in range(1, 6):
    filename = './cifar-10-batches-py/data_batch_' + str(i)
    batch_data = unpickle(filename)
    if len(data) > 0:
        data = np.vstack((data, batch_data['data']))
        labels = np.hstack((labels, batch_data['labels']))
    else:
        data = batch_data['data']
        labels = batch_data['labels']

data = grayscale(data)

x = np.matrix(data)
y = np.array(labels)
horse_indices = np.where(y == 7)[0]
horse_x = x[horse_indices]

input_dim = np.shape(horse_x)[1]
hidden_dim = 100
ae = Autoencoder(input_dim, hidden_dim, 10000)
ae.train(horse_x)

test_data = unpickle('./cifar-10-batches-py/test_batch')
test_x = grayscale(test_data['data'])
test_labels = np.array(test_data['labels'])
test_1 = test_x[13].reshape(1, np.shape(test_x[13])[0])
print(np.shape(test_1))
data_show(test_1, 1)