import numpy as np
import torch
from torchvision.datasets import mnist
import  torchvision.transforms as transforms
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim
from torch import  nn
from matplotlib import pyplot as plt

#定義引數
train_batch_size=64
test_batch_size
 
=128
learning_rate=0.01
num_epoches=3
lr=0.01
momentum=0.5

#定義預處理函式，這些預處理依次放在Compose中
transform=transforms.Compose([transforms.ToTensor(),transforms.Normalize([0.5],[0.5])])#Compose將多個tranform組合，ToTensor轉換形狀，Normalize將會把Tensor正則化。
#下載資料，並對資料進行預處理
train_dataset=mnist.MNIST('./data',train=True,transform=transform,download=True)
test_dataset
 
=mnist.MNIST('./data',train=False,transform=transform)
#data_loader是一個可迭代物件，可以當迭代器使用
train_loader=DataLoader(train_dataset,batch_size=train_batch_size,shuffle=True)
test_loader=DataLoader(test_dataset,batch_size=test_batch_size,shuffle=False)

examples=enumerate(test_loader)
batch_idx,(example_data,example_targets)
 
=next(examples)
fig=plt.figure()
for i in range(6):
    plt.subplot(2,3,i+1)
    plt.tight_layout()
    plt.imshow(example_data[i][0],cmap='gray',interpolation='none')
#plt.show()
#構建網路
class Net(nn.Module):
    def __init__(self,in_dim,n_hidden_1,n_hidden_2,out_dim):
        super(Net,self).__init__()
        self.layer1=nn.Sequential(nn.Linear(in_dim,n_hidden_1),nn.BatchNorm1d(n_hidden_1))#Sequential是將網路的層組合到一起
        self.layer2 = nn.Sequential(nn.Linear(n_hidden_1, n_hidden_2), nn.BatchNorm1d(n_hidden_2))
        self.layer1 = nn.Sequential(nn.Linear(n_hidden_2, out_dim))
    def forward(self,x):
        x=F.relu(self.layer1(x))#將ReLU層新增到網路
        x = F.relu(self.layer2(x))
        x = self.layer1(x)
        return x
#例項化網路
 #檢查網路是否有GPU，有則使用，無則使用cpu
device=torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model=Net(28*28,10,784,10)
model.to(device)
 #定義損失函式和優化器
criterion=nn.CrossEntropyLoss()
optimizer=optim.SGD(model.parameters(),lr=lr,momentum=momentum)

#開始訓練
losses=[]
acces=[]
eval_losses=[]
eval_acces=[]
for epoch in range(num_epoches):
    train_loss=0
    train_acc=0
    model.train()
    #動態修改引數學習率
    if epoch%5==0:
        optimizer.param_groups[0]['lr']*=0.1
    for img,label in train_loader:
        img=img.to(device)
        label=label.to(device)
        img=img.view(img.size(0),-1)
        #前向傳播
        out=model(img)
        loss=criterion(out,label)
        #f反向傳播
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        #記錄誤差
        train_loss+=loss.item()
        #計算分類的準確率
        _,pred=out.max(1)
        num_correct=(pred==label).sum().item()
        acc=num_correct/img.shape[0]
        train_acc+=acc

    losses.append(train_loss/len(train_loader))
    acces.append(train_acc/len(train_loader))
    eval_loss=0
    eval_acc=0
    model.eval()
    for img,label in test_loader:
        img=img.to(device)
        label=label.to(device)
        img=img.view(img.size(0),-1)
        out=model(img)
        loss=criterion(out,label)
        #記錄誤差
        eval_loss+=loss.item()
        #記錄準確李
        _,pred=out.max(1)
        num_correct=(pred==label).sum().item()
        acc=num_correct/img.shape[0]
        eval_acc+=acc

    eval_losses.append(eval_loss / len(test_loader))
    eval_acces.append(eval_acc / len(test_loader))
    print('epoch:{},Train Loss:{:.4f},Train Acc:{:.4f},Test Loss:{:.4f},Test Acc:{:.4f}'
          .format(epoch,train_loss/len(train_loader),train_acc/len(train_loader),eval_loss / len(test_loader),eval_acc / len(test_loader)))

體驗自己開發得深度學習樂趣