import torch
import torch.nn as nn
import torch.nn.functional as F
# 定義一個模型classNet(nn.Module):def__init__(self):super(Net, self).__init__()# 1 input image channel, 6 output channels, 3x3 square convolution# kernel
self.conv1 = nn.Conv2d(1,6,3)
self.conv2 = nn.Conv2d(6,16,3)# an affine operation: y = Wx + b
self.fc1 = nn.Linear(16*6*6,120)# 6*6 from image dimension
self.fc2 = nn.Linear(120,84)
self.fc3 = nn.Linear(84,10)defforward(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
defnum_flat_features(self, x):
size = x.size()[1:]# all dimensions except the batch dimension
num_features =1for s in size:
num_features *= s
return num_features
# 定義了模型還能輸出查看
net = Net()print(net)# 獲取模型參數
params =list(net.parameters())print(len(params))print(params[0].size())# conv1's .weight# 模型前向傳遞,獲得模型結果input= torch.randn(1,1,32,32)
out = net(input)print(out)# 清零梯度,並計算梯度
net.zero_grad()
out.backward(torch.randn(1,10))# 計算損失函數
output = net(input)
target = torch.randn(10)# a dummy target, for example
target = target.view(1,-1)# make it the same shape as output
criterion = nn.MSELoss()
loss = criterion(output, target)print(loss)# 手動更新梯度
learning_rate =0.01for f in net.parameters():
f.data.sub_(f.grad.data * learning_rate)# 優化器自動更新梯度import torch.optim as optim
# create your optimizer
optimizer = optim.SGD(net.parameters(), lr=0.01)# in your training loop:
optimizer.zero_grad()# zero the gradient buffers
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()# Does the update