PyTorch—神经网络Demo
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# 1 input image channel, 6 output channels, 5x5 square convolution kernel
# 输入通道为1,输出通道为6(6个滤波器),卷积窗口大小5 * 5
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) # 输入特征数, 输出特征数
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()
input_data = torch.randn(2, 1, 32, 32) # (batch_size, channels, height, width)
target_data = torch.randn(2, 1, 10)
# 创建优化器
optimizer = optim.SGD(net.parameters(), lr=0.01)
# 损失函数
criterion = nn.MSELoss()
for item_input, item_target in zip(input_data, target_data):
item_input = item_input.unsqueeze(0) # 在前面添加一维
optimizer.zero_grad()
temp_output = net(item_input)
temp_loss = criterion(temp_output, item_target)
temp_loss.backward()
optimizer.step()