softmax回归的从零开始实现

1、读取数据集

import d2lzh.d2lzh as d2l from mxnet import autograd,nd from d2lzh.d2lzh import nn as net #读取数据集 batch_size=256 train_iter,test_iter=d2l.load_data_fashion_mnist(batch_size)

2、初始化模型参数