构建数据Dataset和DataLoader
import torch
from torch import nn, optim
from torch.autograd import Variable
from torch.utils.data import DataLoader, Dataset
from torchvision import datasets, transforms
class myDataset(Dataset):
# torch.utils.data.Dataset 是代表这一数据的抽象类,
# 自己定义你的数 据类继承和重写这个抽象类,非常简单,
# 只需要定义 len一和_getitem一这两个 函数
def __init__(self, ):
self.x_test = [0, 1, 2, 3]
self.y_test = [0, 1, 2, 3]
def __len__(self):
return len(self.x_test)
def __getitem__(self, item):
data = (self.x_test[item], self.y_test[item])
return data
#
data = myDataset()
my_loader = DataLoader(data, batch_size=2, shuffle=True, drop_last=True)
for d in data:
print(d)
print('data[3]: ', data[3])
dataiter = iter(my_loader)
print('dataiter', len(my_loader))
for i in dataiter:
print(i)
构建网络
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),
nn.ReLU(True)
)
self.layer2 = nn.Sequential(
nn.Linear(n_hidden_1, n_hidden_2),
nn.BatchNorm1d(n_hidden_2),
nn.ReLU(True)
)
self.layer3 = nn.Sequential(
nn.Linear(n_hidden_2, out_dim))
def forward(self, x):
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
return x
batch_size = 64
learning_rate = 1e-2
num_epoches = 1
data_tf = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5]),])
train_dataset = datasets.MNIST(root='./data',
train=True,
transform=data_tf,
download=True)
test_dataset = datasets.MNIST(root='./data',
transform=data_tf,
download=True)
train_loader = DataLoader(train_dataset, batch_size=batch_size,shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size,shuffle=True)
model = Net(28*28, 300, 100, 10)
if torch.cuda.is_available():
model = model.cuda()
model.train()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=learning_rate)
#-----------------------------train------------------------------------------------
for epoch in range(num_epoches):
for data in train_loader:
x_train, y_train = data
x_train = x_train.view(x_train.size(0), -1)
if torch.cuda.is_available():
inputs = Variable(x_train).cuda
target = Variable(y_train).cuda
else:
inputs = Variable(x_train)
target = Variable(y_train)
# forward
out = model(inputs)
loss = criterion(out, target)
# backward
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (epoch + 1) :
print('Epoch : [{}/{}], loss: {:.6f}'.format(epoch + 1,
num_epoches,
loss.item()))
#-----------------------------eavl------------------------------------------------
model.eval()
eval_loss = 0
eval_acc = 0
for data in test_loader:
x_test, y_test = data
x_test = x_test.view(x_test.size(0), -1)
if torch.cuda.is_available():
inputs = Variable(x_test, volatile=True).cuda()
target = Variable(y_test, volatile=True).cuda()
else:
inputs = Variable(x_test, volatile=True)
target = Variable(y_test, volatile=True)
out = model(inputs)
loss = criterion(out, target)
eval_loss += loss.item() * target.size(0)
_, pred = torch.max(out, 1)
num_correct = (pred == target).sum()
eval_acc += num_correct.item()
print('Test Loss : {:.6f}, Acc: {:.6f}'.format(
eval_loss / (len(test_dataset)),
eval_acc / (len(test_dataset))
))
参考:
PyTorch之保存加载模型
pytorch
yolov3-pytorch
torch-resnet.py的官方实现
解读官方博客resnet.py
高效使用PyTorch
网友评论