pytorch简单示例

中文文档

简单三层全连接网络

import torch
 
# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10
 
# Create random Tensors to hold inputs and outputs.
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)
 
# Use the nn package to define our model and loss function.
model = torch.nn.Sequential(
          torch.nn.Linear(D_in, H),
          torch.nn.ReLU(),
          torch.nn.Linear(H, D_out),
        )
loss_fn = torch.nn.MSELoss(size_average=False)
 
# Use the optim package to define an Optimizer that will update the weights of
# the model for us. Here we will use Adam; the optim package contains many other
# optimization algoriths. The first argument to the Adam constructor tells the
# optimizer which Tensors it should update.
learning_rate = 1e-4
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
for t in range(500):
  # Forward pass: compute predicted y by passing x to the model.
  y_pred = model(x)
 
  # Compute and print loss.
  loss = loss_fn(y_pred, y)
  print(t, loss.item())
  
  # Before the backward pass, use the optimizer object to zero all of the
  # gradients for the Tensors it will update (which are the learnable weights
  # of the model)
  optimizer.zero_grad()
 
  # Backward pass: compute gradient of the loss with respect to model parameters
  loss.backward()
 
  # Calling the step function on an Optimizer makes an update to its parameters
  optimizer.step()

MNIST识别数字

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
#from torch.autograd import Variable

# Training settings
BATCH_SIZE = 512 # 大概需要2G的显存
EPOCHS = 20 # 总共训练批次
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu") 

# MNIST Dataset
train_dataset = datasets.MNIST(root='./data/',
                train=True, download=True,
                transform=transforms.Compose([
                    transforms.ToTensor(),
                    transforms.Normalize((0.1037,), (0.3081,))
                    ]))

test_dataset = datasets.MNIST(root='./data/',
               train=False,download=True,
               transform=transforms.Compose([
                    transforms.ToTensor(),
                    transforms.Normalize((0.1037,), (0.3081,))
                    ]))

# Data Loader (Input Pipeline)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                      batch_size=BATCH_SIZE,
                      shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                     batch_size=BATCH_SIZE,
                     shuffle=True)


# 定义模型
class ConvNet(nn.Module):
    def __init__(self):
        super().__init__()
        #1*1*28*28
        self.conv1 = nn.Conv2d(1, 10, 5) 
        self.conv2 = nn.Conv2d(10, 20, 3) 
        self.fc1 = nn.Linear(20 * 10 * 10, 500)
        self.fc2 = nn.Linear(500, 10)
        
    def forward(self, x):
        in_size = x.size(0)
        out= self.conv1(x) # 1* 10 * 24 *24
        out = F.relu(out)
        out = F.max_pool2d(out, 2, 2) # 1* 10 * 12 * 12
        out = self.conv2(out) # 1* 20 * 10 * 10
        out = F.relu(out)
        out = out.view(in_size, -1) # 1 * 2000
        out = self.fc1(out) # 1 * 500
        out = F.relu(out)
        out = self.fc2(out) # 1 * 10
        out = F.log_softmax(out, dim = 1)
        return out

# 定义训练函数
def train(model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if (batch_idx + 1) % 30 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))

# 定义测试函数
def test(model, device, test_loader):
    model.eval()
    test_loss =0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction = 'sum') # 将一批的损失相加
            pred = output.max(1, keepdim = True)[1] # 找到概率最大的下标
            correct += pred.eq(target.view_as(pred)).sum().item()
    
    test_loss /= len(test_loader.dataset)
    print("\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%) \n".format(
        test_loss, correct, len(test_loader.dataset),
        100.* correct / len(test_loader.dataset)))

#生成模型和优化器
model = ConvNet().to(DEVICE)
optimizer = optim.Adam(model.parameters())
# 最后开始训练和测试
for epoch in range(1, EPOCHS + 1):
    train(model,  DEVICE, train_loader, optimizer, epoch)
    test(model, DEVICE, test_loader)

tensor

# 创建tensor
torch.FloatTensor       # CPU
torch.cuda.FloatTensor  # GPU
x = torch.Tensor(3, 4)  # 默认为torch.FloatTensor
x = torch.FloatTensor([[1, 2, 3], [4, 5, 6]])
x = torch.IntTensor(2, 4).zero_() # 会改变tensor的函数操作会用一个下划线后缀来标示
x = torch.rand(3, 4)
x = torch.randn(3, 4)
x + y
torch.add(x, y, out = result)
y.add_(x)
# numpy
a = torch.ones(5)
b = a.numpy()
a = np.ones(5)
b = torch.from_numpy(a)
# 复制到gpu
x = x.cuda()
y = y.cuda()
x + y

nn.Module

  所有网络的基类,自己定义的模型也应该继承这个类,Modules也可以包含其它Modules,允许使用树结构嵌入他们,可以将子模块赋值给模型属性.

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)# submodule: Conv2d
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
       x = F.relu(self.conv1(x))
       return F.relu(self.conv2(x))