固定部分参数进行训练¶
有两种实现场景:
- 仅训练某些层
- 暂时固定某些层
仅训练某些层¶
直接在优化器中输入要训练的层参数即可
第一步:在模型中设置不训练的层参数的require_grads
为False
class AlexNet(nn.Module):
def __init__(self, num_classes=1000):
super(AlexNet_SPP, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(64, 192, kernel_size=5, padding=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(192, 384, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(384, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(256, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
)
self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
# 只训练分类器,设置之前参数的require_grads为False
for p in self.parameters():
p.requires_grad = False
self.classifier = nn.Sequential(
nn.Dropout(),
nn.Linear(256 * 50, 4096),
nn.ReLU(inplace=True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(inplace=True),
nn.Linear(4096, num_classes),
)
def forward(self, x):
x = self.features(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.classifier(x)
return x
第二步:在optimizer
中输入待训练的层参数
optimizer = optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), lr=1e-4)
Note:使用filter
和lambda
函数过滤不训练的层参数
暂时固定某些层¶
使用named_parameters过滤
for k, v in model.named_parameters():
print(k, v.requires_grad)
if 'classifier' not in k:
v.requires_grad = False