pytorch1.1.0 + torchvision0.3.0 + cuda10.0.130 + NVIDIA-SMI 470.103.01
import torch
from torchvision import transforms #将图像转化为张量
from torchvision import datasets #对数据集相关处理
from torch.utils.data import DataLoader #下载数据集
import torch.nn.functional as F #使用relu()函数
import torch.optim as optim #优化器
batch_size = 64
"将图像转化成张量:28X28--->1X28X28 CXHXW,并归一化到0-1,0-255--->0-1;0.1307:均值,0.3081:标准差"
transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.1307,),(0.3081,))])
train_dataset = datasets.MNIST(root='../dataset/mnist',train=True,transform=transform,download=True)
test_dataset = datasets.MNIST(root='../dataset/mnist',train=False,transform=transform,download=True)
train_loader = DataLoader(dataset=train_dataset,batch_size=batch_size,shuffle=True)
test_loader = DataLoader(dataset=test_dataset,batch_size=batch_size,shuffle=False)
"2.模型设计"
"输入 NX1X28X28变为 NX784"
"输出为NX10"
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = torch.nn.Conv2d(1,10,kernel_size=5)
self.conv2 = torch.nn.Conv2d(10,20,kernel_size=5)
self.pooling = torch.nn.MaxPool2d(2)
self.fc = torch.nn.Linear(320,10)
def forward(self,x):
batch_size = x.size(0)
x = F.relu(self.pooling(self.conv1(x)))
#x = self.pooling(F.relu(self.conv1(x)))
x = F.relu(self.pooling(self.conv2(x)))
#拉长数据:(n,1,28,28)---->(n,784)
x = x.view(batch_size,-1)
x = self.fc(x)
return x
model = Net()
#该句表示使用GPU,若无GPU,可直接删除
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
model.to(device)
"3.优化器和损失"
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(),lr=0.01,momentum=0.5)
"4.训练和测试"
def train(epoch):
running_loss = 0.0
for batch_idx,data in enumerate(train_loader,0):
inputs,target = data
#该句表示使用GPU,若无GPU,可直接删除
inputs,target = inputs.to(device),target.to(device)
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs,target)
loss.backward()
optimizer.step()
running_loss += loss.item()
if batch_idx % 300 == 299: #每300轮输出一次
print('[%d,%5d] loss: %.3f'%(epoch+1, batch_idx+1,running_loss/300))
running_loss = 0.0
def test():
correct = 0
total = 0
with torch.no_grad():
for data in test_loader:
images,labels = data
#该句表示使用GPU,若无GPU,可直接删除
images, labels = images.to(device), labels.to(device)
outputs = model(images)
# 取出每一行最大值的下标(0-9),dim=1:第一个维度(行);dim=0:第0个维度,列
_,predicted = torch.max(outputs .data,dim=1)
total += labels.size(0) #取NX1矩阵中的N ==batch_size
correct += (predicted == labels).sum().item() #是否为真
#print(correct,total)
print("Accuracy on test set: %d %%"%(100*correct/total)) #正确的/总数
if __name__ == '__main__':
for epoch in range(10):
train(epoch)
test()