《动手学深度学习》之softmax回归（三）代码简洁实现

softmax回归的输出层是一个全连接层，所以我们用一个线性模块就可以了。
因为前面我们数据返回的每个batch样本x的形状为
(batch_size, 1, 28, 28),
所以我们要先用view()将x的形状转换成
(batch_size, 784)才送入全连接层。

import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("..")
import d2lzh_pytorch as d2l
from collections import OrderedDict


# 获取和读取数据-----------------------------------------------
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)


#定义和初始化模型---------------------------------------------
num_inputs = 784
num_outputs = 10

class LinearNet(nn.Module):
    def __init__(self, num_inputs, num_outputs):
        super(LinearNet, self).__init__()
        self.linear = nn.Linear(num_inputs, num_outputs)
    def forward(self, x):                              # x shape: (batch, 1, 28, 28)
        print(x.shape[0])
        y = self.linear(x.view(x.shape[0], -1))
        return y

net = LinearNet(num_inputs, num_outputs)


# 本函数已保存在d2lzh_pytorch包中方便以后使用
#将对x的形状转换的这个功能自定义一个FlattenLayer
class FlattenLayer(nn.Module):
    def __init__(self):
        super(FlattenLayer, self).__init__()
    def forward(self, x): # x shape: (batch, *, *, ...)
        return x.view(x.shape[0], -1)



net = nn.Sequential(
    # FlattenLayer(),
    # nn.Linear(num_inputs, num_outputs)
    OrderedDict([
        ('flatten', FlattenLayer()),
        ('linear', nn.Linear(num_inputs, num_outputs))
    ])
)

#使用均值为0、标准差为0.01的正态分布随机初始化模型的权重参数。
init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0) 


#softmax和交叉熵损失函数---------------------------------------
loss = nn.CrossEntropyLoss()
#定义优化算法-----------------------------------------------
optimizer = torch.optim.SGD(net.parameters(), lr=0.1)

#训练模型-----------------------------------------------------
num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)

关于d2lzh_pytorch这个包,我会在一篇博客中持续更新