import torch
import numpy as np
from torch import nn,optim
from torch.autograd import Variable
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
#训练集
train_dataset = datasets.MNIST('./',
train=True,
transform=transforms.ToTensor(),
download=True)
#测试集
test_dataset = datasets.MNIST('./',
train=False,
transform=transforms.ToTensor(),
download=True)
#批次大小
batch_size=64
#装载训练集
train_loader = DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
#装载测试集
test_loader = DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=True)
#定义网络结构
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(784,10)
self.softmax = nn.Softmax(dim=1)
def forward(self,x):
#([64,1,28,28])->(64,784)
#全连接层数据需要2维
#改变数据形状
x= x.view(x.size()[0],-1)
x= self.fc1(x)
x= self.softmax(x)
return x
#定义模型
model = Net()
#定义代价函数
mse_loss = nn.MSELoss()
#定义优化器
#学习率
LR=0.5
optimizer = optim.SGD(model.parameters(),LR)
def train():
for i,data in enumerate(train_loader):
#获得一个批次的数据和标签
inputs, labels = data
#获得模型预测结果(64,10)
out = model(inputs)
#把数据标签变成独热编码
labels = labels.reshape(-1,1)
#tensor.scatter(dim,index,src)
#dim 对哪个维度进行独热编码
#index 将src中的对应值放到tensor的哪个位置
#src 插入index的值
one_hot = torch.zeros(inputs.shape[0],10).scatter(1,labels,1)
#计算loss ,mse_loss的两个数据shape要一致
loss = mse_loss(out,one_hot)
#梯度清零
optimizer.zero_grad()
#计算梯度
loss.backward()
#修改权值
optimizer.step()
def test():
correct = 0
for i,data in enumerate(test_loader):
inputs, labels =data
out = model(inputs)
_, predicted =torch.max(out, 1)
correct+=(predicted == labels).sum()
print("Test acc:{0}".format(correct.item()/len(test_dataset)))
#开始训练
for epoch in range(10):
print('epoch:',epoch+1)
train()
test()