手写数字的MNIST数据集

• http://yann.lecun.com/exdb/mnist/

train-images-idx3-ubyte.gz: training set images (9912422 bytes)
train-labels-idx1-ubyte.gz: training set labels (28881 bytes)
t10k-images-idx3-ubyte.gz: test set images (1648877 bytes)
t10k-labels-idx1-ubyte.gz: test set labels (4542 bytes)

百度镜像：

• https://dataset.bj.bcebos.com/mnist/train-images-idx3-ubyte.gz
• https://dataset.bj.bcebos.com/mnist/train-labels-idx1-ubyte.gz
• https://dataset.bj.bcebos.com/mnist/t10k-images-idx3-ubyte.gz
• https://dataset.bj.bcebos.com/mnist/t10k-labels-idx1-ubyte.gz

  # 使用 python paddle 下载
  import paddle
  from paddle.vision.transforms import Compose, Normalize
  
  transform = Compose([Normalize(mean=[127.5],
                                 std=[127.5],
                                 data_format='CHW')])
  # 使用transform对数据集做归一化
  print('download training data and load training data')
  train_dataset = paddle.vision.datasets.MNIST(mode='train', transform=transform)
  test_dataset = paddle.vision.datasets.MNIST(mode='test', transform=transform)
  print('load finished')