import torch.nn as nn
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import torch.optim as optim
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 6, 5)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16*5*5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
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(x.size()[0], -1) #reshape '-1'means auto
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
input = Variable(t.randn(1,1,32,32))
net = Net()
#print('net.conv1.bias.grad')
#print(net.conv1.bias.grad)
weight = 0
learning_rate = 0.01
#weight = weight - learning_rate*gradient
optimizer = optim.SGD(net.parameters(), lr = 0.01)
optimizer.zero_grad()
output = net(input)
#print(out.size)
#print(net)
target = Variable(t.arange(0,10))
target = target.view([1,10])
criterion = nn.MSELoss()
loss = criterion(output, target)
net.zero_grad()
#print('net.conv1.bias.grad')
#print(net.conv1.bias.grad)
loss.backward()
for var in net.parameters():
#print(var)
var.data.sub_(var.grad.data * learning_rate) #inplace
optimizer.step()PyTorch 第一个简单例子
最后编辑于 ：
©著作权归作者所有,转载或内容合作请联系作者
- 文/潘晓璐 我一进店门，熙熙楼的掌柜王于贵愁眉苦脸地迎上来，“玉大人，你说我怎么就摊上这事。” “怎么了？”我有些...
- 文/花漫 我一把揭开白布。 她就那样静静地躺着，像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上，一...
- 文/苍兰香墨 我猛地睁开眼，长吁一口气：“原来是场噩梦啊……” “哼！你这毒妇竟也来了？” 一声冷哼从身侧响起，我...
