两层卷积网络的示例
# convolutional neural network (2 convolutional layers)
class ConvNet(nn.Module):
def __init__(self, num_classes=10):
super(ConvNet, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(16),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.fc = nn.Linear(7*7*32, num_classes)
def forward(self, x):
out = self.layer1(x)
out = self.layer2(out)
out = out.reshape(out.size(0), -1)
out = self.fc(out)
return out
model = ConvNet(num_classes).to(device)
计算模型整体参数量
num_parameters = sum(torch.numel(parameter) for parameter in model.parameters())
查看网络中的参数
可以通过model.state_dict()或者model.named_parameters()函数查看现在的全部可训练参数(包括通过继承得到的父类中的参数)
params = list(model.named_parameters())
(name, param) = params[28]
print(name)
print(param.grad)
print('-------------------------------------------------')
(name2, param2) = params[29]
print(name2)
print(param2.grad)
print('----------------------------------------------------')
(name1, param1) = params[30]
print(name1)
print(param1.grad)
模型权重初始化
注意 model.modules() 和 model.children() 的区别:model.modules() 会迭代地遍历模型的所有子层,而 model.children() 只会遍历模型下的一层。
# Common practise for initialization.
for layer in model.modules():
if isinstance(layer, torch.nn.Conv2d):
torch.nn.init.kaiming_normal_(layer.weight, mode='fan_out',
nonlinearity='relu')
if layer.bias is not None:
torch.nn.init.constant_(layer.bias, val=0.0)
elif isinstance(layer, torch.nn.BatchNorm2d):
torch.nn.init.constant_(layer.weight, val=1.0)
torch.nn.init.constant_(layer.bias, val=0.0)
elif isinstance(layer, torch.nn.Linear):
torch.nn.init.xavier_normal_(layer.weight)
if layer.bias is not None:
torch.nn.init.constant_(layer.bias, val=0.0)
# Initialization with given tensor.
layer.weight = torch.nn.Parameter(tensor)
部分层使用预训练模型
model.load_state_dict(torch.load('model.pth'), strict=False)
将在 GPU 保存的模型加载到 CPU
model.load_state_dict(torch.load('model.pth', map_location='cpu'))
更新网络的权重
使用神经网络的时候你想要使用不同种类的方法诸如:SGD, Nesterov-SGD, Adam, RMSProp, etc.
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
扫描二维码关注公众号,回复:
10306933 查看本文章