Neural network TypeError:forward（）缺少1个必需的位置参数：'；c'；

我创建了VGG16的简化版本：

class VGG16COMBO(nn.Module):
    
    def __init__(self, num_classes):
        super(VGG16COMBO, self).__init__()

        # calculate same padding:
        # (w - k + 2*p)/s + 1 = o
        # => p = (s(o-1) - w + k)/2

        self.block_1 = nn.Sequential(
            nn.Conv2d(in_channels=1,
                      out_channels=64,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      # (1(32-1)- 32 + 3)/2 = 1
                      padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.Conv2d(in_channels=64,
                      out_channels=64,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2),
                         stride=(2, 2))
        )

        self.block_2 = nn.Sequential(
            nn.Conv2d(in_channels=64,
                      out_channels=128,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(128),
            nn.ReLU(),
            nn.Conv2d(in_channels=128,
                      out_channels=128,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(128),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2),
                         stride=(2, 2))
        )
        
        self.block_3 = nn.Sequential(
            nn.Conv2d(in_channels=128,
                      out_channels=256,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.Conv2d(in_channels=256,
                      out_channels=256,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.Conv2d(in_channels=256,
                      out_channels=256,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2),
                         stride=(2, 2))
        )

        self.block_4 = nn.Sequential(
            nn.Conv2d(in_channels=256,
                      out_channels=512,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU(),
            nn.Conv2d(in_channels=512,
                      out_channels=512,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU(),
            nn.Conv2d(in_channels=512,
                      out_channels=512,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2),
                         stride=(2, 2))
        ) 


        self.classifier = nn.Sequential(
            nn.Linear(2048, 4096),
            nn.ReLU(True),
            nn.Dropout(p=0.25),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
            nn.Dropout(p=0.25),
            nn.Linear(4096, num_classes),
        )

    def forward(self, m, c):

        m = self.block_1(m)
        m = self.block_2(m)
        m = self.block_3(m)
        m = self.block_4(m)
        m = m.view(m.size(0), -1)
        m = self.classifier(m)

        c = self.block_1(c)
        c = self.block_2(c)
        c = self.block_3(c)
        c = self.block_4(c)
        c = c.view(c.size(0), -1)
        c = self.classifier(c)

        x = torch.cat((m, c), dim=1)
        return x

你们可以看到，在前进中，我传递了两个元素，m和c。m指的是MNIST，c指的是CIFAR10，因为我想要一个多输入神经网络（或一个具有共享权重的网络）。 然后：

这是我的培训职能：

#train da modificare con entrambi i dataset
def train(net, loaders, optimizer, criterion, epochs=20, dev=dev, save_param = False, model_name="valerio"):
    try:
        net = net.to(dev)
        #print(net)
        # Initialize history
        history_loss = {"train": [], "val": [], "test": []}
        history_accuracy = {"train": [], "val": [], "test": []}
        # Store the best val accuracy
        best_val_accuracy = 0

        # Process each epoch
        for epoch in range(epochs):
            # Initialize epoch variables
            sum_loss = {"train": 0, "val": 0, "test": 0}
            sum_accuracy = {"train": 0, "val": 0, "test": 0}
            # Process each split
            for split in ["train", "val", "test"]:
                if split == "train":
                  net.train()
                else:
                  net.eval()
                # Process each batch
                for (input, labels) in loaders[split]:
                    # Move to CUDA
                    input = input.to(dev)
                    labels = labels.to(dev)
                    # Reset gradients
                    optimizer.zero_grad()
                    # Compute output
                    pred = net(input)
                    #pred = pred.squeeze(dim=1) # Output shape is [Batch size, 1], but we want [Batch size]
                    labels = labels.unsqueeze(1)
                    labels = labels.float()
                    loss = criterion(pred, labels)
                    # Update loss
                    sum_loss[split] += loss.item()
                    # Check parameter update
                    if split == "train":
                        # Compute gradients
                        loss.backward()
                        # Optimize
                        optimizer.step()
                    # Compute accuracy
                    #pred_labels = pred.argmax(1) + 1
                    pred_labels = (pred >= 0.5).long() # Binarize predictions to 0 and 1
                    batch_accuracy = (pred_labels == labels).sum().item()/input.size(0)
                    # Update accuracy
                    sum_accuracy[split] += batch_accuracy
            # Compute epoch loss/accuracy
            epoch_loss = {split: sum_loss[split]/len(loaders[split]) for split in ["train", "val", "test"]}
            epoch_accuracy = {split: sum_accuracy[split]/len(loaders[split]) for split in ["train", "val", "test"]}

            # Store params at the best validation accuracy
            if save_param and epoch_accuracy["val"] > best_val_accuracy:
              #torch.save(net.state_dict(), f"{net.__class__.__name__}_best_val.pth")
              torch.save(net.state_dict(), f"{model_name}_best_val.pth")
              best_val_accuracy = epoch_accuracy["val"]

            # Update history
            for split in ["train", "val", "test"]:
                history_loss[split].append(epoch_loss[split])
                history_accuracy[split].append(epoch_accuracy[split])
            # Print info
            print(f"Epoch {epoch+1}:",
                  f"TrL={epoch_loss['train']:.4f},",
                  f"TrA={epoch_accuracy['train']:.4f},",
                  f"VL={epoch_loss['val']:.4f},",
                  f"VA={epoch_accuracy['val']:.4f},",
                  f"TeL={epoch_loss['test']:.4f},",
                  f"TeA={epoch_accuracy['test']:.4f},")
    except KeyboardInterrupt:
        print("Interrupted")
    finally:
        # Plot loss
        plt.title("Loss")
        for split in ["train", "val", "test"]:
            plt.plot(history_loss[split], label=split)
        plt.legend()
        plt.show()
        # Plot accuracy
        plt.title("Accuracy")
        for split in ["train", "val", "test"]:
            plt.plot(history_accuracy[split], label=split)
        plt.legend()
        plt.show()

def itr_merge(*itrs):
    for itr in itrs:
        for v in itr:
            yield v

但是当我训练的时候

# Train model
train(modelcombo, loaders, optimizer, criterion, epochs=10, dev=dev)

我得到这个错误：

TypeError: forward() missing 1 required positional argument: 'c'

我必须改变什么，网络还是训练功能？我认为问题出在培训功能上，因为我必须通过加载器，加载器cifar，但我不知道如何通过。特别是，我必须在将mnist的装载机和cifar的装载机传递给培训功能之前对它们进行cat操作，或者我必须在装载机[split]和装载机[split]中修改装载机[split]中（输入，标签）的

：

编辑：我创建了这个函数：

#train da modificare con entrambi i dataset
def train(net, loaders, optimizer, criterion, epochs=20, dev=dev, save_param = False, model_name="valerio"):
    try:
        net = net.to(dev)
        #print(net)
        # Initialize history
        history_loss = {"train": [], "val": [], "test": []}
        history_accuracy = {"train": [], "val": [], "test": []}
        # Store the best val accuracy
        best_val_accuracy = 0

        # Process each epoch
        for epoch in range(epochs):
            # Initialize epoch variables
            sum_loss = {"train": 0, "val": 0, "test": 0}
            sum_accuracy = {"train": 0, "val": 0, "test": 0}
            # Process each split
            for split in ["train", "val", "test"]:
                if split == "train":
                  net.train()
                else:
                  net.eval()
                # Process each batch
                for (input, labels) in loaders[split]:
                    # Move to CUDA
                    input = input.to(dev)
                    labels = labels.to(dev)
                    # Reset gradients
                    optimizer.zero_grad()
                    # Compute output
                    pred = net(input)
                    #pred = pred.squeeze(dim=1) # Output shape is [Batch size, 1], but we want [Batch size]
                    labels = labels.unsqueeze(1)
                    labels = labels.float()
                    loss = criterion(pred, labels)
                    # Update loss
                    sum_loss[split] += loss.item()
                    # Check parameter update
                    if split == "train":
                        # Compute gradients
                        loss.backward()
                        # Optimize
                        optimizer.step()
                    # Compute accuracy
                    #pred_labels = pred.argmax(1) + 1
                    pred_labels = (pred >= 0.5).long() # Binarize predictions to 0 and 1
                    batch_accuracy = (pred_labels == labels).sum().item()/input.size(0)
                    # Update accuracy
                    sum_accuracy[split] += batch_accuracy
            # Compute epoch loss/accuracy
            epoch_loss = {split: sum_loss[split]/len(loaders[split]) for split in ["train", "val", "test"]}
            epoch_accuracy = {split: sum_accuracy[split]/len(loaders[split]) for split in ["train", "val", "test"]}

            # Store params at the best validation accuracy
            if save_param and epoch_accuracy["val"] > best_val_accuracy:
              #torch.save(net.state_dict(), f"{net.__class__.__name__}_best_val.pth")
              torch.save(net.state_dict(), f"{model_name}_best_val.pth")
              best_val_accuracy = epoch_accuracy["val"]

            # Update history
            for split in ["train", "val", "test"]:
                history_loss[split].append(epoch_loss[split])
                history_accuracy[split].append(epoch_accuracy[split])
            # Print info
            print(f"Epoch {epoch+1}:",
                  f"TrL={epoch_loss['train']:.4f},",
                  f"TrA={epoch_accuracy['train']:.4f},",
                  f"VL={epoch_loss['val']:.4f},",
                  f"VA={epoch_accuracy['val']:.4f},",
                  f"TeL={epoch_loss['test']:.4f},",
                  f"TeA={epoch_accuracy['test']:.4f},")
    except KeyboardInterrupt:
        print("Interrupted")
    finally:
        # Plot loss
        plt.title("Loss")
        for split in ["train", "val", "test"]:
            plt.plot(history_loss[split], label=split)
        plt.legend()
        plt.show()
        # Plot accuracy
        plt.title("Accuracy")
        for split in ["train", "val", "test"]:
            plt.plot(history_accuracy[split], label=split)
        plt.legend()
        plt.show()

def itr_merge(*itrs):
    for itr in itrs:
        for v in itr:
            yield v

以这种方式编辑培训功能：

#train da modificare con entrambi i dataset
def train2(net, loaders, loaders_cifar, optimizer, criterion, epochs=20, dev=dev, save_param = False, model_name="valerio"):
    try:
        net = net.to(dev)
        #print(net)
        # Initialize history
        history_loss = {"train": [], "val": [], "test": []}
        history_accuracy = {"train": [], "val": [], "test": []}
        # Store the best val accuracy
        best_val_accuracy = 0

        # Process each epoch
        for epoch in range(epochs):
            # Initialize epoch variables
            sum_loss = {"train": 0, "val": 0, "test": 0}
            sum_accuracy = {"train": 0, "val": 0, "test": 0}
            # Process each split
            for split in ["train", "val", "test"]:
                if split == "train":
                  net.train()
                else:
                  net.eval()
                # Process each batch
                for x in itr_merge(loaders[split], loaders_cifar[split]):
                  for (input, labels) in loaders[split]:
                      # Move to CUDA
                      input = input.to(dev)
                      labels = labels.to(dev)
                      # Reset gradients
                      optimizer.zero_grad()
                      # Compute output
                      pred = net(input)
                      #pred = pred.squeeze(dim=1) # Output shape is [Batch size, 1], but we want [Batch size]
                      labels = labels.unsqueeze(1)
                      labels = labels.float()
                      loss = criterion(pred, labels)
                      # Update loss
                      sum_loss[split] += loss.item()
                      # Check parameter update
                      if split == "train":
                          # Compute gradients
                          loss.backward()
                          # Optimize
                          optimizer.step()
                      # Compute accuracy
                      #pred_labels = pred.argmax(1) + 1
                      pred_labels = (pred >= 0.5).long() # Binarize predictions to 0 and 1
                      batch_accuracy = (pred_labels == labels).sum().item()/input.size(0)
                      # Update accuracy
                      sum_accuracy[split] += batch_accuracy
            # Compute epoch loss/accuracy
            epoch_loss = {split: sum_loss[split]/len(loaders[split]) for split in ["train", "val", "test"]}
            epoch_accuracy = {split: sum_accuracy[split]/len(loaders[split]) for split in ["train", "val", "test"]}

            # Store params at the best validation accuracy
            if save_param and epoch_accuracy["val"] > best_val_accuracy:
              #torch.save(net.state_dict(), f"{net.__class__.__name__}_best_val.pth")
              torch.save(net.state_dict(), f"{model_name}_best_val.pth")
              best_val_accuracy = epoch_accuracy["val"]

            # Update history
            for split in ["train", "val", "test"]:
                history_loss[split].append(epoch_loss[split])
                history_accuracy[split].append(epoch_accuracy[split])
            # Print info
            print(f"Epoch {epoch+1}:",
                  f"TrL={epoch_loss['train']:.4f},",
                  f"TrA={epoch_accuracy['train']:.4f},",
                  f"VL={epoch_loss['val']:.4f},",
                  f"VA={epoch_accuracy['val']:.4f},",
                  f"TeL={epoch_loss['test']:.4f},",
                  f"TeA={epoch_accuracy['test']:.4f},")
    except KeyboardInterrupt:
        print("Interrupted")
    finally:
        # Plot loss
        plt.title("Loss")
        for split in ["train", "val", "test"]:
            plt.plot(history_loss[split], label=split)
        plt.legend()
        plt.show()
        # Plot accuracy
        plt.title("Accuracy")
        for split in ["train", "val", "test"]:
            plt.plot(history_accuracy[split], label=split)
        plt.legend()
        plt.show()

---

但是我仍然有相同的错误

是，如果有两个数据点输入，那么在这里传递两个参数

pred = net(input1,input2) #input1 ---> mnist ,input2 ---> cifar

---

在训练中你在哪里通过了m和c这两项？我没有通过，这就是问题所在。我只通过了1个“加载器”，但我必须通过2个加载器，一个用于mnist，一个用于civaryes，但我还必须修改for循环，对吗？确保在加载器[split]中为（输入，标签）解压

中的两个数据加载器。

是的，但我如何才能做到这一点？我很困惑，我必须在培训之前对两个加载程序进行cat/展平/合并，或者在培训中我必须选择两个加载程序？正确，两个数据集都应该有一个数据加载程序，然后在培训循环中，你必须将它们解包