搭建網絡&保存網絡
以下內容是根據torch官網和莫煩python學習所得
搭建網絡
-
新建網絡
class Net(torch.nn.Module): def __init__(self, n_feature, n_hidden, n_output): super(Net, self).__init__() self.hidden = torch.nn.Linear(n_feature, n_hidden) self.predict = torch.nn.Linear(n_hidden, n_output) def forward(self, x): x = F.relu(self.hidden(x)) x = self.predict(x) return x net1 = Net(1, 10, 1) # 這是我們用這種方式搭建的 net1
-
快速新建
net2 = torch.nn.Sequential( torch.nn.Linear(1, 10), torch.nn.ReLU(), torch.nn.Linear(10, 1) )
-
二者對比
print(net1) Net( (hidden): Linear(in_features=1, out_features=10, bias=True) (predict): Linear(in_features=10, out_features=1, bias=True) ) ####################################################### print(net2) Sequential( (0): Linear(in_features=1, out_features=10, bias=True) (1): ReLU() (2): Linear(in_features=10, out_features=1, bias=True) )
保存網絡
-
新建網絡
torch.manual_seed(1) # reproducible # 假數據 x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1) # x data (tensor), shape=(100, 1) y = x.pow(2) + 0.2*torch.rand(x.size()) # noisy y data (tensor), shape=(100, 1) def save(): # 建網絡 net1 = torch.nn.Sequential( torch.nn.Linear(1, 10), torch.nn.ReLU(), torch.nn.Linear(10, 1) ) optimizer = torch.optim.SGD(net1.parameters(), lr=0.5) loss_func = torch.nn.MSELoss() # 訓練 for t in range(100): prediction = net1(x) loss = loss_func(prediction, y) optimizer.zero_grad() loss.backward() optimizer.step()
-
保存網絡
torch.save(net1, 'net.pkl') # 保存整個網絡 torch.save(net1.state_dict(), 'net_params.pkl') # 只保存網絡中的參數 (速度快, 佔內存少)
-
提取網絡
# 提取整個網絡 def restore_net(): # restore entire net1 to net2 net2 = torch.load('net.pkl') prediction = net2(x)
# 只提取網絡參數 def restore_params(): # 新建 net3 net3 = torch.nn.Sequential( torch.nn.Linear(1, 10), torch.nn.ReLU(), torch.nn.Linear(10, 1) ) # 將保存的參數複製到 net3 net3.load_state_dict(torch.load('net_params.pkl')) prediction = net3(x)
源代碼
import torch
import matplotlib.pyplot as plt
# torch.manual_seed(1) # reproducible
# fake data
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1) # x data (tensor), shape=(100, 1)
y = x.pow(2) + 0.2*torch.rand(x.size()) # noisy y data (tensor), shape=(100, 1)
# The code below is deprecated in Pytorch 0.4. Now, autograd directly supports tensors
# x, y = Variable(x, requires_grad=False), Variable(y, requires_grad=False)
def save():
# save net1
net1 = torch.nn.Sequential(
torch.nn.Linear(1, 10),
torch.nn.ReLU(),
torch.nn.Linear(10, 1)
)
optimizer = torch.optim.SGD(net1.parameters(), lr=0.5)
loss_func = torch.nn.MSELoss()
for t in range(100):
prediction = net1(x)
loss = loss_func(prediction, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
# plot result
plt.figure(1, figsize=(10, 3))
plt.subplot(131)
plt.title('Net1')
plt.scatter(x.data.numpy(), y.data.numpy())
plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
# 2 ways to save the net
torch.save(net1, 'net.pkl') # save entire net
torch.save(net1.state_dict(), 'net_params.pkl') # save only the parameters
def restore_net():
# restore entire net1 to net2
net2 = torch.load('net.pkl')
prediction = net2(x)
# plot result
plt.subplot(132)
plt.title('Net2')
plt.scatter(x.data.numpy(), y.data.numpy())
plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
def restore_params():
# restore only the parameters in net1 to net3
net3 = torch.nn.Sequential(
torch.nn.Linear(1, 10),
torch.nn.ReLU(),
torch.nn.Linear(10, 1)
)
# copy net1's parameters into net3
net3.load_state_dict(torch.load('net_params.pkl'))
prediction = net3(x)
# plot result
plt.subplot(133)
plt.title('Net3')
plt.scatter(x.data.numpy(), y.data.numpy())
plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
plt.show()
# save net1
save()
# restore entire net (may slow)
restore_net()
# restore only the net parameters
restore_params()