100 lines
3.7 KiB
Plaintext
100 lines
3.7 KiB
Plaintext
import torch as t
|
||
import torchvision as tv
|
||
import torchvision.transforms as transforms
|
||
import torch.nn as nn
|
||
import torch.nn.functional as F
|
||
|
||
#错误的还未学习
|
||
########## 超参数设置 ##########
|
||
epochs = 200
|
||
learning_rate = 0.001
|
||
batch_size = 256
|
||
gpu_ids = [0, 1, 2]
|
||
|
||
|
||
########## 一、数据加载与预处理 ##########
|
||
transform = transforms.Compose([
|
||
transforms.ToTensor(),
|
||
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
|
||
])
|
||
trainset = tv.datasets.CIFAR10(root='./data/', train=True, download=True, transform=transform)
|
||
testset = tv.datasets.CIFAR10(root='./data/', train=False, download=True, transform=transform)
|
||
trainloader = t.utils.data.DataLoader(trainset, batch_size=batch_size, shuffle=True, num_workers=4)
|
||
testloader = t.utils.data.DataLoader(testset, batch_size=batch_size, shuffle=False, num_workers=4)
|
||
|
||
|
||
########## 二、定义神经网络 ##########
|
||
class LeNet(nn.Module):
|
||
def __init__(self):
|
||
super(LeNet, self).__init__()
|
||
# (in_channels, out_channels, kernel_size, stride, padding)
|
||
self.conv1 = nn.Conv2d(3, 6, 5, 1, 0)
|
||
self.conv2 = nn.Conv2d(6, 16, 5, 1, 0)
|
||
self.fc1 = nn.Linear(16 * 5 * 5, 120)
|
||
self.fc2 = nn.Linear(120, 84)
|
||
self.fc3 = nn.Linear(84, 10)
|
||
|
||
def forward(self, x):
|
||
x = F.max_pool2d(F.relu(self.conv1(x)), 2, 2)
|
||
x = F.max_pool2d(F.relu(self.conv2(x)), 2, 2)
|
||
x = x.view(x.size()[0], -1)
|
||
x = F.relu(self.fc1(x))
|
||
x = F.relu(self.fc2(x))
|
||
x = self.fc3(x)
|
||
return x
|
||
|
||
|
||
########## 三、训练神经网络 ##########
|
||
# 神经网络实例化
|
||
net = LeNet()
|
||
if (len(gpu_ids) == 0) or (not t.cuda.is_available()):
|
||
# gpu_ids列表为空, 或者没GPU可用，则设置为GPU模式。
|
||
device = t.device("cpu")
|
||
print("Train Mode : CPU")
|
||
elif t.cuda.is_available() and len(gpu_ids) > 1:
|
||
# gpu_ids列表大于1，表明想用多个GPU训练
|
||
device = t.device("cuda:0")
|
||
net = nn.DataParallel(net, device_ids=gpu_ids)
|
||
print("Train Mode : Multi GPU;", gpu_ids)
|
||
else:
|
||
# gpu_ids列表等于1，表明想用一个GPU训练
|
||
device = t.device("cuda:" + str(gpu_ids[0]) if t.cuda.is_available() else "cpu")
|
||
print("Train Mode : One GPU;", device)
|
||
net = net.to(device)
|
||
print("\n", "##" * 10, " NetWork ", "##" * 10, "\n", net, "\n", "##" * 26, "\n")
|
||
# 定义损失函数和优化器
|
||
criterion = nn.CrossEntropyLoss()
|
||
optimizer = t.optim.SGD(net.parameters(), lr=learning_rate, momentum=0.9)
|
||
# 开始训练
|
||
for epoch in range(epochs):
|
||
running_loss = 0.0
|
||
for i, (inputs, labels) in enumerate(trainloader):
|
||
inputs, labels = inputs.to(device), labels.to(device)
|
||
optimizer.zero_grad()
|
||
outputs = net(inputs)
|
||
loss = criterion(outputs, labels)
|
||
loss.backward()
|
||
optimizer.step()
|
||
running_loss += loss.item()
|
||
print("Epoch%03d: Training_loss = %.5f" % (epoch + 1, running_loss))
|
||
|
||
# 保存模型并进行验证
|
||
if (epoch + 1) % 10 == 0:
|
||
if len(gpu_ids) > 1:
|
||
t.save(net.module.state_dict(), "Cifar10_LeNet_Epoch" + str(epoch + 1) + ".pth")
|
||
else:
|
||
t.save(net.state_dict(), "Cifar10_LeNet_Epoch" + str(epoch + 1) + ".pth")
|
||
correct = 0
|
||
all = 0
|
||
with t.no_grad():
|
||
for (inputs, labels) in testloader:
|
||
inputs, labels = inputs.to(device), labels.to(device)
|
||
outputs = net(inputs)
|
||
_, predicted = t.max(outputs, 1)
|
||
all += inputs.size()[0]
|
||
correct += (predicted == labels).sum().item()
|
||
print("###" * 15)
|
||
print("Epoch%03d: TestSet_Accuracy = %.3f" % (epoch + 1, correct / all))
|
||
print("###" * 15)
|
||
|
||
print("Train Done!") |