pytorch固定部分参数
不用梯度
如果是Variable,则可以初始化时指定
j = Variable(torch.randn(5,5), requires_grad=True)
但是如果是m = nn.Linear(10,10)
是没有requires_grad
传入的
for i in m.parameters():
i.requires_grad=False
另外一个小技巧就是在nn.Module里,可以在中间插入这个
for p in self.parameters():
p.requires_grad=False
# eg 前面的参数就是False,而后面的不变
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)
for p in self.parameters():
p.requires_grad=False
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def freeze(test_net):
ct = 0
for child in test_net.children():
ct += 1
if ct < 3:
for param in child.parameters():
param.requires_grad = False
过滤
optimizer.SGD(filter(lambda p: p.requires_grad, model.parameters()), lr=1e-3)