这个算是给后续做项目做个预热环节(≧▽≦)/啦啦啦，已经开始写网络层，loss，优化函数这些都有，写起来也不是很费劲，主要就是接口使用上不太熟悉，代码还是很好理解的
官网上也给出了对应的一般训练网络的步骤：
定义网络结构迭代你的数据集让网络来处理你的输入计算损失计算梯度进行方向传播根据对应的优化算法进行参数更新（例子给的就是简单的梯度下降更新规则） #导入对应依赖包 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, 3x3 square convolution # 输入通道数，输出通道数， 卷积核大小 self.conv1 = nn.Conv2d(1, 6, 3) self.conv2 = nn.Conv2d(6, 16, 3) #这个就是全连接网络，输入输出维度定义 self.fc1 = nn.Linear(16*6*6, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10) #前向传播部分，加了ReLU和最大池化操作 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)) 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 # 这个就是定义了一个函数，把特征拉成向量，用来做后续的全连接操作 def num_flat_features(self, x): size = x.size()[1:] num_features = 1 for s in size: num_features *= s return num_features net = Net() print(net) Net( (conv1): Conv2d(1, 6, kernel_size=(3, 3), stride=(1, 1)) (conv2): Conv2d(6, 16, kernel_size=(3, 3), stride=(1, 1)) (fc1): Linear(in_features=576, 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) ) # 参数列表，LZ稍微增加了点，输出了这个网络的总的参数 params = list(net.parameters()) print(len(params)) print(params[0].size()) num_total = 0 for s in range(0, len(params)): num_par = 1 for num in params[s].size(): num_par *= num num_total += num_par print(num_total) 10 torch.Size([6, 1, 3, 3]) 81194 #随机初始化对应维度作为输入 #注意输入顺序 nSamples x nChannels x Height x Width input = torch.randn(1, 1, 32, 32) out = net(input) print(out) tensor([[-0.0035, 0.0065, -0.0847, -0.0913, -0.0093, 0.0638, -0.1184, 0.0701, 0.1883, 0.0905]], grad_fn=<AddmmBackward>) #要手动将梯度置零 net.zero_grad() out.backward(torch.randn(1, 10)) output = net(input) target = torch.randn(10) target = target.view(1, -1) #制定loss计算规则，这里就是均方误差 criterion = nn.MSELoss() # 计算loss loss = criterion(output, target) print(loss) tensor(0.6834, grad_fn=<MseLossBackward>) print(loss.grad_fn) print(loss.grad_fn.next_functions[0][0]) print(loss.grad_fn.next_functions[0][0].next_functions[0][0]) <MseLossBackward object at 0x7fe3ec0bf4a8> <AddmmBackward object at 0x7fe3ec0bf9e8> <AccumulateGrad object at 0x7fe3ec0bf4a8> net.zero_grad() print('conv1.bias.grad before backward') print(net.conv1.bias.grad) #进行反向传播， loss.backward() #对应参数得到梯度 print("conv1.bias.grad after backward") print(net.conv1.bias.grad) conv1.bias.grad before backward tensor([0., 0., 0., 0., 0., 0.]) conv1.bias.grad after backward tensor([-0.0009, 0.0055, 0.0078, -0.0062, 0.0008, 0.0101]) #学习率更新后，跟新参数 learning_rate = 0.01 for f in net.parameters(): #print(f.data) f.data.sub_(f.grad.data*learning_rate) #print(f.data) #导入优化函数依赖包，使用随机梯度下降 import torch.optim as optim optimizer = optim.SGD(net.parameters(), lr = 0.01) optimizer.zero_grad() output = net(input) loss = criterion(output, target) loss.backward() optimizer.step()好像也还行，能理解，继续下面的学习。。。
参考地址： https://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#sphx-glr-beginner-blitz-neural-networks-tutorial-py
