Hi everyone, I am new user on pytorch. Currently i’m trying to implement an LSTM and GRU model. The LSTM training is doing well, but when i switch into GRU training im facing some issues.
Any advice?
AttributeError Traceback (most recent call last)
in
---- > 1 train ( modelGRU , train_list , val_list , path , seq , epoch , batch_size , criterionGRU , optimizerGRU , model_type = “GRU” )
in train (model, train_list, val_list, path, seq, epoch, batch_size, criterion, optimizer, model_type)
52 # print(x.size(),hidden[0].size() )
53 if model_type == “GRU” :
—> 54 hidden = hidden . data
55 else :
56 hidden = tuple ( [ e . data for e in hidden ] )
AttributeError :‘tuple’ object has no attribute’data’
class GRUNet(nn.Module):
def __init__(self,in_size,h_size,n_layers,fc_out,out_size,dropout=0.5):
super(GRUNet, self).__init__()
self.gru = nn.GRU(input_size=in_size,hidden_size=h_size,num_layers=n_layers,dropout=dropout,bias=False)
self.fc = nn.Linear(in_features=h_size,out_features=fc_out,bias=False)
self.relu = nn.ReLU(inplace=True)
self.out = nn.Linear(in_features=fc_out,out_features=out_size,bias=False)
self.tanh = nn.Tanh()
def forward(self, x, hidden):
out, hidden = self.gru(x, hidden)
x = self.fc(x)
x = self.relu(x)
x = self.out(x)
x = self.tanh(x)
return x, hidden
class MyLstm(nn.Module):
def __init__(self,in_size,h_size,n_layers,fc_out,out_size,dropout=0.5):
super(MyLstm, self).__init__()
self.lstm = nn.LSTM(input_size=in_size,hidden_size=h_size,num_layers=n_layers,dropout=dropout,bias=False)
self.fc = nn.Linear(in_features=h_size,out_features=fc_out,bias=False)
self.relu = nn.ReLU(inplace=True)
self.out = nn.Linear(in_features=fc_out,out_features=out_size,bias=False)
self.tanh = nn.Tanh()
def forward(self,x,hidden):
x, hidden = self.lstm(x,hidden)
# x = x[-1:]
x = self.fc(x)
x = self.relu(x)
x = self.out(x)
x = self.tanh(x)
return x, hidden
def train(model,train_list,val_list,path,seq,epoch,batch_size,criterion,optimizer,model_type):
for e in range(epoch):
train_data = load_data(train_list,batch_size)
a_loss = 0
a_size = 0
model.train()
for x,y in train_data:
x,y = x.to(device),y.to(device)
bs = x.size()[1]
h1 = torch.zeros((n_layers,bs,h_size)).to("cuda:0")
h2 = torch.zeros((n_layers,bs,h_size)).to("cuda:0")
hidden = (h1,h2)
# hidden = (hidden[0].detach(),hidden[1].detach())
# print(x.size(),hidden[0].size())
if model_type == "GRU":
hidden = hidden.data
else:
hidden = tuple([e.data for e in hidden])
model.zero_grad()
pred,hidden = model(x,hidden)
loss = criterion(pred,y)
loss.backward()
nn.utils.clip_grad_norm_(model.parameters(),5)
optimizer.step()
a_loss += loss.detach()
a_size += bs
# print(e,a_loss/a_size*1e+6)
model.eval()
with torch.no_grad():
val_data = load_data(val_list,batch_size)
b_loss = 0
b_size = 0
for x,y in val_data:
x,y = x.to(device),y.to(device)
bs = x.size()[1]
h1 = torch.zeros((n_layers,bs,h_size)).to("cuda:0")
h2 = torch.zeros((n_layers,bs,h_size)).to("cuda:0")
hidden = (h1,h2)
pred,hidden = model(x,hidden)
loss = criterion(pred,y)
b_loss += loss.detach()
b_size += bs
print("epoch: {} - train_loss: {} - val_loss: {}".format(e+1,float(a_loss.item()/a_size*1e+6),b_loss.item()/b_size*1e+6))
train(modelGRU,train_list,val_list,path,seq,epoch,batch_size,criterionGRU,optimizerGRU,model_type="GRU")```
Thank you