我正在尝试为LSTM和GRU建立训练模型。LSTM运行得很完美，但是当我切换到GRU训练时，就出现了尺寸不匹配等错误。
这是我的代码
path = "new_z_axis"device = "cuda:0"in_size = 3h_size = 50n_layers = 3fc = 20out = 1batch_size = 16seq = 100epoch = 100learning_rate = 1e-3ratio = 0.8checkpoint = os.path.join("checkpoints","model_"+path+"_"+str(in_size)+".pth")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, hiddenclass 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, hiddendef 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] # hidden = (hidden[0].detach(),hidden[1].detach())# print(x.size(),hidden[0].size()) if model_type == "GRU": h1 = torch.zeros((n_layers,bs,h_size)).to("cuda:0") hidden = h1 hidden = hidden.data else: 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 = tuple([e.data for e in hidden]) model.zero_grad() print (len(hidden)) 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] if model_type == "GRU": h1 = torch.zeros((n_layers,bs,h_size)).to("cuda:0") hidden = h1 hidden = hidden.data else: 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 = tuple([e.data for e in hidden]) 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")这是我得到的错误
RuntimeError Traceback (most recent call last) <ipython-input-9-a382a9688da2> in <module> ---- > 1 train ( modelGRU , train_list , val_list , path , seq , epoch , batch_size , criterionGRU , optimizerGRU , model_type = "GRU" )<ipython-input-6-4565cf358824> in train (model, train_list, val_list, path, seq, epoch, batch_size, criterion, optimizer, model_type) 61 model . zero_grad ( ) 62 print ( len ( hidden ) ) ---> 63 pred , hidden = model ( x , hidden ) 64 loss = criterion ( pred , y ) 65 loss .backward ( )~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in __call__ (self, *input, **kwargs) 539 result = self . _slow_forward ( * input , ** kwargs ) 540 else : --> 541 result = self . forward ( * input , ** kwargs ) 542 for hook in self . _forward_hooks . values ( ) : 543 hook_result = hook ( self , input , result )<ipython-input-5-4ecae472cc96> in forward (self, x, hidden) 11 def forward ( self , x , hidden ) : 12 out , hidden = self . gru ( x , hidden ) ---> 13 x = self . fc ( x ) 14 x = self . relu ( x ) 15 x =self . out ( x )~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in __call__ (self, *input, **kwargs) 539 result = self . _slow_forward ( * input , ** kwargs ) 540 else : --> 541 result = self . forward ( * input , ** kwargs ) 542 for hook in self . _forward_hooks . values ( ) : 543 hook_result = hook ( self , input , result )~ \ Anaconda3 \ lib \ site-packages \ torch \ nn \ modules \ linear.py in forward (self, input) 85 86 def forward ( self , input ) : ---> 87 return F . Linear ( the Input , Self . Weight , Self . negative bias ) 88 89 def extra_repr ( Self ) : ~\Anaconda3\lib\site-packages\torch\nn\functional.py in linear (input, weight, bias) 1370 ret = torch . addmm ( bias , input , weight . t ( ) ) 1371 else : -> 1372 output = input . matmul ( weight . t ( ) ) 1373 if bias is not None : 1374 output += biasRuntimeError : size mismatch, m1: [1600 x 3], m2: [50 x 20] at C:/w/1/s/tmp_conda_3.7_104508/conda/conda-bld/pytorch_1572950778684/work/aten/src\THC/ generic/THCTensorMathBlas.cu:290有什么建议吗？
回答：
