Pytorch深度学习基础——Softmax回归实现

Pytorch实现Softmax回归

FashionMNIST数据集

我们将会使用FashionMNIST这个数据集，这相当于机器学习当中的“Hello World”，无论什么时候提出一个新的分类算法，都想知道该算法在这个数据集上的表现如何。

获取数据集

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
train_iter=torch.utils.data.DataLoader(mnist_train,batch_size=batch_size,shuffle=True,num_workers=num_workers)
test_iter=torch.utils.data.DataLoader(mnist_test,batch_size=batch_size,shuffle=True,num_workers=num_workers)

定义模型并训练

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):
        y=self.linear(X.view(X.shape[0],-1))
        return y
net=LinearNet(num_inputs,num_outputs);
print(net)
class FattenLayer(nn.Module):
	##处理数据集的shape
    def __init__(self):
        super(FattenLayer,self).__init__()
    def forward(self,X):
        return X.view(X.shape[0],-1)
net=nn.Sequential(
    FattenLayer(),
    LinearNet(num_inputs,num_outputs)
)
init.normal_(net[1].linear.weight,mean=0,std=0.01)
init.constant_(net[1].linear.bias,val=0)
loss=nn.CrossEntropyLoss()
optimizer=torch.optim.SGD(net.parameters(),lr=0.1)
num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)