来源：https://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#backprop
来源里面有比较详细的例子。这里挑几点比较重点的作为recap
定义一个模型 import torch import torch.nn as nn import torch.nn.functional as F class Net(nn.Module): def __init__(self): super(Net, self).__init__() # 1 input image channel, 6 output channels, 5x5 square convolution # kernel self.conv1 = nn.Conv2d(1, 6, 5) self.conv2 = nn.Conv2d(6, 16, 5) # an affine operation: y = Wx + b self.fc1 = nn.Linear(16 * 5 * 5, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10) def forward(self, x): # Max pooling over a (2, 2) window x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2)) # If the size is a square you can only specify a single number x = F.max_pool2d(F.relu(self.conv2(x)), 2) x = x.view(-1, self.num_flat_features(x)) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x def num_flat_features(self, x): size = x.size()[1:] # all dimensions except the batch dimension num_features = 1 for s in size: num_features *= s return num_features net = Net() print(net) out: Net( (conv1): Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1)) (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1)) (fc1): Linear(in_features=400, out_features=120, bias=True) (fc2): Linear(in_features=120, out_features=84, bias=True) (fc3): Linear(in_features=84, out_features=10, bias=True) )我们定义网络模型的时候，定义了forward函数之后，backward函数会自动生成，所以不用我们调用。
损失函数loss functions：可以使用nn.MSELoss() 计算均方误差
计算的流程图
input -> conv2d -> relu -> maxpool2d -> conv2d -> relu -> maxpool2d -> view -> linear -> relu -> linear -> relu -> linear -> MSELoss -> lossbackprop可以使用：loss.backward()
更细权重可以使用：optimizer.step()
完整的代码如下：
class Net(nn.Module): def __init__(self): super(Net, self).__init__() # 1 input image channel, 6 output channels, 5x5 square convolution # kernel self.conv1 = nn.Conv2d(1, 6, 5) self.conv2 = nn.Conv2d(6, 16, 5) # an affine operation: y = Wx + b self.fc1 = nn.Linear(16 * 5 * 5, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10) def forward(self, x): # Max pooling over a (2, 2) window x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2)) # If the size is a square you can only specify a single number x = F.max_pool2d(F.relu(self.conv2(x)), 2) x = x.view(-1, self.num_flat_features(x)) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x def num_flat_features(self, x): size = x.size()[1:] # all dimensions except the batch dimension num_features = 1 for s in size: num_features *= s return num_features net = Net() print(net) # 随机初始化输入 inputs = torch.randn(1, 1, 32, 32) target = torch.randn(10) # a dummy target, for example target = target.view(1, -1) # make it the same shape as output # create your optimizer optimizer = optim.SGD(net.parameters(), lr=0.01) # in your training loop: optimizer.zero_grad() # zero the gradient buffers output = net(inputs) loss = nn.MSELoss(output, target) loss.backward() optimizer.step() # Does the update print(output)如果想使用pytorch测试MNIST，可以参考：https://github.com/pytorch/examples/tree/master/mnist
