获取数据集
导入需要的包和模块
%matplotlib inline
import d2lzh as d2l
from mxnet.gluon import data as gdata
import sys
import time
#第一次调用时会自动从网上获取数据集。
mnist_train = gdata.vision.FashionMNIST(train=True)
mnist_test = gdata.vision.FashionMNIST(train=False)
#查看获取数据集数量
len(mnist_train),len(mnist_test)
#获取第一个样本的图像和标签
feature, label = mnist_train[0]
#查看类型
feature.shape, feature.dtype
#将数值标签转成相应的文本标签
def get_fashion_mnist_labels(labels):
test_labels = ['t-shirt','trouser','pullover','dress','coat','sandal','shirt','sneaker','bag','ankle boot',]
return [test_labels[int(i)] for i in labels]
#此函数用于一行里画出多张图像和对应标签
def show_fashion_mnist(images, labels):
d2l.use_svg_display()
_, figs = d2l.plt.subplots(1, len(images), figsize=(12, 12))
for f, img, lbl in zip(figs, images, labels):
f.imshow(img.reshape((28, 28)).asnumpy())
f.set_title(lbl)
f.axes.get_xaxis().set_visible(False)
f.axes.get_yaxis().set_visible(False)
#查看数据集前9个样本的图像内容和文本标签
X, y = mnist_train[0:9]
show_fashion_mnist(X, get_fashion_mnist_labels(y))
读取小批量
batch_size = 256 #读取样本数的batch_size的小批量数
transformer = gdata.vision.transforms.ToTensor()
if sys.platform.startswith('win'):
num_workers = 0 #添加0个进程数
else:
num_workers = 4
train_iter = gdata.DataLoader(mnist_train.transform_first(transformer),batch_size, shuffle=True, num_workers=num_workers)
test_iter = gdata.DataLoader(mnist_test.transform_first(transformer),batch_size, shuffle=False, num_workers=num_workers)