python - Pytorch GRU 错误 RuntimeError：大小不匹配，m1：[1600 x 3]，m2：[50 x 20]

Question

目前，我正在尝试为 LSTM 和 GRU 制作训练模型。LSTM 运行良好，但是一旦我切换到 GRU 训练，就会弹出错误，例如大小不匹配错误。

这是我的代码

    path = "new_z_axis"
    device = "cuda:0"
    in_size = 3
    h_size = 50
    n_layers = 3
    fc = 20
    out = 1
    batch_size = 16
    seq = 100
    epoch = 100
    learning_rate = 1e-3
    ratio = 0.8
    checkpoint = 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, 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]
                
    #             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 (last last call last) in ---- > 1 train ( modelGRU , train_list , val_list , path , seq ， epoch ， batch_size ，criteriaGRU ， optimizerGRU ， model_type = "GRU" ）

在 train (model, train_list, val_list, path, seq, epoch, batch_size, criteria, optimizer, model_type) 61 模型中。zero_grad ( ) 62 print (len ( hidden ) ) ---> 63 pred , hidden = model ( x , hidden ) 64 loss =criteria ( pred , y ) 65 loss .backward ( )

~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in call (self, *input, **kwargs) 539 result = self 。_slow_forward（* 输入，** kwargs）540 其他：-> 541 结果 = 自我。forward (* input, ** kwargs) 542 for hook in self 。_forward_hooks 。值（）：543 hook_result = hook（自我，输入，结果）

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 = 自我。relu (x) 15 x =自己。出 ( x )

~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in call (self, *input, **kwargs) 539 result = self 。_slow_forward（* 输入，** kwargs）540 其他：-> 541 结果 = 自我。forward (* input, ** kwargs) 542 for hook in self 。_forward_hooks 。值（）：543 hook_result = hook（自我，输入，结果）

~\Anaconda3\lib\site-packages\torch\nn\modules\linear.py in forward (self, input) 85
86 def forward (self, input) : ---> 87 return F。线性（输入，自我。权重，​​自我。负偏差）88 89 def extra_repr（自我）：

~\Anaconda3\lib\site-packages\torch\nn\functional.py 线性（输入，权重，偏差） 1370 ret = torch 。addmm (bias, input, weight.t()) 1371 else: -> 1372 output = input. matmul（重量。t（））1373如果偏差不是无：1374输出+=偏差

RuntimeError：大小不匹配，m1：[1600 x 3]，m2：[50 x 20] 在 C:/w/1/s/tmp_conda_3.7_104508/conda/conda-bld/pytorch_1572950778684/work/aten/src\THC/通用/THCTensorMathBlas.cu:290

有什么建议吗？谢谢

标签： pythonmachine-learningpytorchlstm

Answer 1

这可能与您没有将输出传递给's函数nn.GRU中的第一个线性层的事实有关：GRUNetforward

    def forward(self, x, hidden):
        out, hidden = self.gru(x, hidden)
        x = self.fc(out)