演练验证
目的:就是使用训练集中的数据,分为两部分,共60000张,分48000张给训练,分12000张给验证。(注意:此处的验证集和之后的test验证集不同;此处的验证集,权当是我们为了确定训练参数,而专门从本应是训练集的数据,分割出的一部分)
代码:
from keras.datasets import mnist
from keras import models
from keras import layers
from keras.utils import to_categorical
import matplotlib.pyplot as plt
#加载mnist数据集
(train_images, train_labels), (test_images, test_labels) = mnist.load_data();
print("train_images=", train_images.shape)
print("train_labels", train_labels)
print("test_images=", test_images.shape)
print("test_labels", test_labels)
#将train_images和train_labels放入网络训练;然后test_images放入预测,与test_labels做比较
#网络结构
network = models.Sequential()
network.add(layers.Dense(512, activation='relu', input_shape=(28*28,)))
network.add(layers.Dense(10, activation='softmax'))
network.summary();#看一下网络结构
#准备图像数据
train_images = train_images.reshape((60000, 28 * 28)