python输入数据的维度_keras分类模型中的输入数据与标签的维度实例

在《python深度学习》这本书中。

一、21页mnist十分类

导入数据集

from keras.datasets import mnist

(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

初始数据维度：

>>> train_images.shape

(60000, 28, 28)

>>> len(train_labels)

60000

>>> train_labels

array([5, 0, 4, ..., 5, 6, 8], dtype=uint8)

数据预处理：

train_images = train_images.reshape((60000, 28 * 28))

train_images = train_images.astype('float32') / 255

train_labels = to_categorical(train_labels)

之后：

print(train_images, type(train_images), train_images.shape, train_images.dtype)

print(train_labels, type(train_labels), train_labels.shape, train_labels.dtype)

结果：

[[0. 0. 0. ... 0. 0. 0.]

[0. 0. 0. ... 0. 0. 0.]

[0. 0. 0. ... 0. 0. 0.]</