Python学习笔记--Pythorch学习1手写体识别

import torch
import torchvision
from torch import nn
from torch.nn import functional as F
from torch import optim
import torchision
from matplotlib import pyplot as plt
from utils import plot_image,plot_cruve,one_hot

##一次处理图片的数量
batch_size=512

##加载数据集 load_dataset
train_loader = torch.utils.data.DataLoader(
torchvision.datasets.MNIST(‘mnist_data’, train=True, download=True,
transform=torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(
(0.1307,), (0.3081,))
])),
batch_size=batch_size, shuffle=True)

test_loader = torch.utils.data.DataLoader(
torchvision.datasets.MNIST(‘mnist_data/’, train=False, download=True,
transform=torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(
(0.1307,), (0.3081,))
])),
batch_size=batch_size, shuffle=False)
x,y=next((iter=(train_loader))
print(x.shape,y.shape,x.min(),x.max())
plot_image(x,y,‘image sample’)

#创建一个三层的网络
class Net(nn.Module):
def init(self):
super(Net, self).init()

    #xw+b  一层，线性层
    self.fc1=nn.Linear(28*28,256)
    self.fc2=nn.Linear(256,64)
    self.fc3=nn.Linear(64,10)
##计算过程,网络创建过程
def forward(self, x):
    ##x:[b,1,28,28]
    ##h1=wx+b
    x=F.relu(self.fc1(x))
    #h2=relu(h1w2+b2))
    x=F.relu(self.fc2(x))
    ##softmax激活函数可不加
    #h3=w3h2+b3
    x=self.fc3(x)
    return x

#创建一个网络对象
net=Net()
#【2w1,w2,w3,b1,b2,b3】
optimizer=optim.SGD(met.parameters(),lr=0.1,momentum=0.9)

##可视化
train_loader[]
##训练
for epoch in range(3):

for batch_idx,(x,y) in enumerate(train_loader):
    #x:
    #print(x.shape,y.shape)
    ##输出
    #[b,1,28,29]=>[b,feature]
    x=x.view(x.size(0),28*28)
    #=》【b,10】
    out=net(x)
    #[b,10]
    y_onehot=one_hot(y)
    #loss=mse(out,y_onehot)
    loss=F.mse_loss(out,y_onehot)
    #对梯度清零
    optimizer.zero_grad()
    ##梯度，利用优化器
    loss.backward()
    #w'-lr*grad  更新梯度
    optimizer.step()
    train_loss.append(loss.item())
    if batch_idx%10==0:
        print(epoch,batch_idx,loss.item())

plot_cruve(train_loss)
#得到比较好的[w1,b1,w2,b2,w3,b3]

total_correct=0
for x,y in test_loader:
x=x.view(x.size(0),28*28)
out=net(x)
#out:[b,10]=>pred:[d]
pred=out.argmax(dim=1)
#转换成数值类型
correct=pred.eq(y).sum().float().item()
total_correct+=correct

total_num=len(test_loader.dataset)
acc=total_correct/total_num
print(‘test acc:’,acc)
x,y=next(iter(test_loader))

out=net(x.view(x.size(0),28*28))
pred=out.argmax(dim=1)
plot_image(x,prd,‘test’)