def load_datasets(show_examples=False):
X_train = load_MNIST.load_train_images()
y_train = load_MNIST.load_train_labels()
X_test = load_MNIST.load_test_images()
y_test = load_MNIST.load_test_labels()
if show_examples is True:
sample = X_train[1, :, :]
plt.imshow(sample)
plt.show()
print('样例的矩阵形式为:\n {}'.format(sample))
return X_train, X_test, y_train, y_test
from sklearn import preprocessing
from sklearn.neural_network import MLPClassifier
import time
import sys
import os
sys.path.append(os.path.join(os.getcwd(), 'Modules'))
import load_MNIST
# TODO: 1.载入数据
start = time.time()
train_images = load_MNIST.load_train_images()
train_labels = load_MNIST.load_train_labels()
test_images = load_MNIST.load_test_images()
test_labels = load_MNIST.load_test_labels()
print("载入数据集共耗时: {:.3f}s".format(time.time() - start))
# TODO: 2.数据划分及预处理I
# 标准调整形态的方法
# X_train = train_images.reshape(train_images.shape[0], train_images.shape[1]*train_images.shape[2])/255
# 此处，因为我们已经知道的样本的形态，所以可以直接书写值
X_train = train_images.reshape(60000, 28 * 28) / 255
y_train = train_labels
X_test = test_images.reshape(10000, 28 * 28) / 255
y_test = test_labels
# 为了提高训练速度，我们只提取10%的样本进行演示
X_train_lite = X_train[0:5999, :]