导入minist数据集，使用request下载数据集

from pathlib import Path
import requests
DATA_PATH = Path("data")
PATH = DATA_PATH / "mnist"
PATH.mkdir(parents=True, exist_ok=True)
URL = "http://deeplearning.net/data/mnist/"
FILENAME = "mnist.pkl.gz"if not (PATH / FILENAME).exists():content = requests.get(URL + FILENAME).content(PATH / FILENAME).open("wb").write(content)

数据集为numpy数组格式，并已使用pickle（一种用于序列化数据的python特定格式）存储。

import pickle
import gzipwith gzip.open((PATH / FILENAME).as_posix(), "rb") as f:((x_train, y_train), (x_valid, y_valid), _) = pickle.load(f, encoding="latin-1")

生成28*28的图像

from matplotlib import pyplot
import numpy as nppyplot.imshow(x_train[0].reshape((28, 28)), cmap="gray")
print(x_train.shape)

将数据分为训练集合和测试集合

import torchx_train, y_train, x_valid, y_valid = map(torch.tensor, (x_train, y_train, x_valid, y_valid)
)
n, c = x_train.shape
x_train, x_train.shape, y_train.min(), y_train.max()
print(x_train, y_train)
print(x_train.shape)
print(y_train.min(), y_train.max())

计算模型的准确率

def accuracy(out, yb):preds = torch.argmax(out, dim=1)return (preds == yb).float().mean()

关于argmax函数的dim=1的看法：dim为1的时候，列的维度就消失了，dim为0的时候，行的维度就消失了。