这是我定义的模型,它是具有2个完全连接层的简单lstm。
import copy
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
class mylstm(nn.Module):
def __init__(self,input_dim, output_dim, hidden_dim,linear_dim):
super(mylstm, self).__init__()
self.hidden_dim=hidden_dim
self.lstm=nn.LSTMCell(input_dim,self.hidden_dim)
self.linear1=nn.Linear(hidden_dim,linear_dim)
self.linear2=nn.Linear(linear_dim,output_dim)
def forward(self, input):
out,_=self.lstm(input)
out=nn.Dropout(p=0.3)(out)
out=self.linear1(out)
out=nn.Dropout(p=0.3)(out)
out=self.linear2(out)
return out
x_train
和x_val
是形状为(4478,30)
的float数据帧,而y_train
和y_val
是形状为(4478,10)
x_train.head()
Out[271]:
0 1 2 3 ... 26 27 28 29
0 1.6110 1.6100 1.6293 1.6370 ... 1.6870 1.6925 1.6950 1.6905
1 1.6100 1.6293 1.6370 1.6530 ... 1.6925 1.6950 1.6905 1.6960
2 1.6293 1.6370 1.6530 1.6537 ... 1.6950 1.6905 1.6960 1.6930
3 1.6370 1.6530 1.6537 1.6620 ... 1.6905 1.6960 1.6930 1.6955
4 1.6530 1.6537 1.6620 1.6568 ... 1.6960 1.6930 1.6955 1.7040
[5 rows x 30 columns]
x_train.shape
Out[272]: (4478, 30)
定义变量并做一次bp,我可以发现波动损失为1.4941
model=mylstm(30,10,200,100).double()
from torch import optim
optimizer=optim.RMSprop(model.parameters(), lr=0.001, alpha=0.9)
criterion=nn.L1Loss()
input_=torch.autograd.Variable(torch.from_numpy(np.array(x_train)))
target=torch.autograd.Variable(torch.from_numpy(np.array(y_train)))
input2_=torch.autograd.Variable(torch.from_numpy(np.array(x_val)))
target2=torch.autograd.Variable(torch.from_numpy(np.array(y_val)))
optimizer.zero_grad()
output=model(input_)
loss=criterion(output,target)
loss.backward()
optimizer.step()
moniter=criterion(model(input2_),target2)
moniter
Out[274]: tensor(1.4941, dtype=torch.float64, grad_fn=<L1LossBackward>)
但是我再次调用了正向函数,由于辍学的随机性,我得到了一个不同的数字
moniter=criterion(model(input2_),target2)
moniter
Out[275]: tensor(1.4943, dtype=torch.float64, grad_fn=<L1LossBackward>)
我应该怎么做才能消除预测短语中的所有遗漏?
我尝试了eval()
:
moniter=criterion(model.eval()(input2_),target2)
moniter
Out[282]: tensor(1.4942, dtype=torch.float64, grad_fn=<L1LossBackward>)
moniter=criterion(model.eval()(input2_),target2)
moniter
Out[283]: tensor(1.4945, dtype=torch.float64, grad_fn=<L1LossBackward>)
并传递一个附加参数p来控制辍学:
import copy
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
class mylstm(nn.Module):
def __init__(self,input_dim, output_dim, hidden_dim,linear_dim,p):
super(mylstm, self).__init__()
self.hidden_dim=hidden_dim
self.lstm=nn.LSTMCell(input_dim,self.hidden_dim)
self.linear1=nn.Linear(hidden_dim,linear_dim)
self.linear2=nn.Linear(linear_dim,output_dim)
def forward(self, input,p):
out,_=self.lstm(input)
out=nn.Dropout(p=p)(out)
out=self.linear1(out)
out=nn.Dropout(p=p)(out)
out=self.linear2(out)
return out
model=mylstm(30,10,200,100,0.3).double()
output=model(input_)
loss=criterion(output,target)
loss.backward()
optimizer.step()
moniter=criterion(model(input2_,0),target2)
Traceback (most recent call last):
File "<ipython-input-286-e49b6fac918b>", line 1, in <module>
output=model(input_)
File "D:\Users\shan xu\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 489, in __call__
result = self.forward(*input, **kwargs)
TypeError: forward() missing 1 required positional argument: 'p'
但是他们俩都没有。
答案 0 :(得分:0)
您必须在nn.Dropout
中定义您的__init__
层,并将其分配给模型以响应调用eval()
。
因此,像这样更改模型应该对您有用:
class mylstm(nn.Module):
def __init__(self,input_dim, output_dim, hidden_dim,linear_dim,p):
super(mylstm, self).__init__()
self.hidden_dim=hidden_dim
self.lstm=nn.LSTMCell(input_dim,self.hidden_dim)
self.linear1=nn.Linear(hidden_dim,linear_dim)
self.linear2=nn.Linear(linear_dim,output_dim)
# define dropout layer in __init__
self.drop_layer = nn.Dropout(p=p)
def forward(self, input):
out,_= self.lstm(input)
# apply model dropout, responsive to eval()
out= self.drop_layer(out)
out= self.linear1(out)
# apply model dropout, responsive to eval()
out= self.drop_layer(out)
out= self.linear2(out)
return out
如果您进行更改,则这样的退出将在您致电eval()
时不起作用。
注意:如果以后要继续训练,则需要在模型上调用train()
退出评估模式。
您还可以在此处找到一个使用eval()
进行评估的辍学示例:
nn.Dropout vs. F.dropout pyTorch
答案 1 :(得分:0)
正如其他答案所述,希望在模型的__init__
方法中定义辍学层,以便模型可以跟踪每个预定义层的所有信息。当模型的状态改变时,它将通知所有层并进行一些相关的工作。例如,在调用model.eval()
时,您的模型将停用停用层,但直接传递所有激活。通常,如果要停用退出层,最好使用__init__
模块以nn.Dropout
方法定义退出层。
答案 2 :(得分:0)
我添加这个答案只是因为我现在正面临着同样的问题,同时试图通过辍学分歧重塑贝叶斯主动学习。如果您需要保持退出活动状态(例如,为相同的测试实例引导一组不同的预测),则只需将模型置于训练模式,则无需定义自己的退出层。 由于在pytorch中您需要定义自己的预测函数,因此只需向其添加一个参数即可,如下所示:
def predict_class(model, test_instance, active_dropout=False):
if active_dropout:
model.train()
else:
model.eval()