问题描述
这是我用于lstm网络的代码,我将其实例化并传递给Cuda设备,但仍然收到隐藏和输入不在同一设备中的错误
class LSTM_net(nn.Module):
def __init__(self,input_size,hidden_size,output_size):
super(LSTM_net,self).__init__()
self.hidden_size = hidden_size
self.lstm_cell = nn.LSTM(input_size,hidden_size)
self.h2o = nn.Linear(hidden_size,output_size)
self.softmax = nn.Logsoftmax(dim=1)
def forward(self,input,hidden_0=None,hidden_1=None,hidden_2=None):
input=resnet(input)
input=input.unsqueeze(0)
out_0,hidden_0 = self.lstm_cell(input,hidden_0)
out_1,hidden_1 = self.lstm_cell(out_0+input,hidden_1)
out_2,hidden_2 = self.lstm_cell(out_1+input,hidden_2)
output = self.h2o(hidden_2[0].view(-1,self.hidden_size))
output = self.softmax(output)
return output,hidden_0,hidden_1,hidden_2
def init_hidden(self,batch_size = 1):
return (torch.zeros(1,batch_size,self.hidden_size),torch.zeros(1,self.hidden_size))
net1=LSTM_net(input_size=1000,hidden_size=1000,output_size=100)
net1=net1.to(device)
pic of connections that I want to make,plz guide me to implement it
click here for an image of error massege
解决方法
确保为forward()方法提供的hidden_0驻留在GPU内存中,或者理想情况下将其作为参数张量存储在模型中,以便优化器将其更新并由model.cuda()移至gpu。
第二个解决方案的示例,该模型中的hidden_0驻留在模型中(在init中添加并在forward()中用作self.hidden_0
):
class LSTM_net(nn.Module):
def __init__(self,input_size,hidden_size,output_size):
super(LSTM_net,self).__init__()
self.hidden_size = hidden_size
self.lstm_cell = nn.LSTM(input_size,hidden_size)
self.h2o = nn.Linear(hidden_size,output_size)
self.softmax = nn.LogSoftmax(dim=1)
self.hidden_0 = torch.nn.parameter.Parameter(torch.zeros(1,batch_size,self.hidden_size)) #taken from init_hidden,assuming that's the intended shape
def forward(self,input,hidden_0=None,hidden_1=None,hidden_2=None):
input=resnet(input)
input=input.unsqueeze(0)
out_0,hidden_0 = self.lstm_cell(input,self.hidden_0)
out_1,hidden_1 = self.lstm_cell(out_0+input,hidden_1)
out_2,hidden_2 = self.lstm_cell(out_1+input,hidden_2)
output = self.h2o(hidden_2[0].view(-1,self.hidden_size))
output = self.softmax(output)
return output,hidden_0,hidden_1,hidden_2
,
编辑:我想我现在看到了问题。尝试更改
def init_hidden(self,batch_size = 1):
return (torch.zeros(1,self.hidden_size),torch.zeros(1,self.hidden_size))
到
def init_hidden(self,self.hidden_size).cuda(),self.hidden_size).cuda())
这是因为init_hidden方法创建的每个张量都不是函数父对象中的数据属性。因此,当您将cuda()应用于模型对象的实例时,它们将不会应用cuda()。
尝试在所有涉及的张量/变量和模型上调用.cuda()。
net1.cuda() # net1.to(device) for device == cuda:0 works fine also
# cuda() is more succinct,though
input.cuda()
# now,calling net1 on a tensor named input should not produce the error.
out = net1(input)