RuntimeError：“nll_loss_forward_reduce_cuda_kernel_2d_index”未针对“Int”实现：Pytorch

Question

因此，我尝试按照本教程使用 Pytorch 编写聊天机器人。

代码：（最小的，可重复的）

tags = []
for intent in intents['intents']:
    tag = intent['tag']
    tags.append(tag)

tags = sorted(set(tags))

X_train = []
X_train = np.array(X_train)

class ChatDataset(Dataset):
    def __init__(self):
        self.n_sample = len(X_train)
        self.x_data = X_train

#Hyperparameter
batch_size = 8
hidden_size = 47
output_size = len(tags)
input_size = len(X_train[0])
learning_rate = 0.001
num_epochs = 1000


dataset = ChatDataset()
train_loader = DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True, num_workers=0)

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # using gpu
model = NeuralNet(input_size, hidden_size, output_size).to(device)

# loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

for epoch in range(num_epochs):
    for (words, labels) in train_loader:
        words = words.to(device)
        labels = labels.to(device)

        #forward
        outputs = model(words)
        loss = criterion(outputs, labels) #the line where it is showing the problem

        #backward and optimizer step
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    if (epoch +1) % 100 == 0:
        print(f'epoch {epoch+1}/{num_epochs}, loss={loss.item():.4f}')

print(f'final loss, loss={loss.item():.4f}')

完整代码（如果需要）

我在尝试获取损失函数时收到此错误。

RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Int'

追溯：

Traceback (most recent call last): File "train.py", line 91, in <module> loss = criterion(outputs, labels) File "C:\Users\PC\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "C:\Users\PC\anaconda3\lib\site-packages\torch\nn\modules\loss.py", line 1150, in forward return F.cross_entropy(input, target, weight=self.weight, File "C:\Users\PC\anaconda3\lib\site-packages\torch\nn\functional.py", line 2846, in cross_entropy return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing) RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Int'

但看看教程，它似乎在那里完美地工作，但在我的情况下却不然。

现在做什么？

谢谢。

Answer 1

torch.LongTensor就我而言，我通过在将数据存储到 GPU 之前将目标类型转换为 来解决这个问题，如下所示：

for inputs, targets in data_loader:
    targets = targets.type(torch.LongTensor)   # casting to long
    inputs, targets = inputs.to(device), targets.to(device)
    ...
    ...
 
    loss = self.criterion(output, targets)

Answer 2

我猜您遵循了 YouTube 上的 Python Engineer 教程（我也遵循了并且遇到了同样的问题！）。@Phoenix 的解决方案对我有用。我所需要做的就是像这样投射标签（他称之为目标）：

for epoch in range(num_epochs):
    for (words, labels) in train_loader:
        words = words.to(device)
        labels = labels.type(torch.LongTensor) # <---- Here (casting)
        labels = labels.to(device)
        
        #forward
        outputs = model(words)
        loss = criterion(outputs, labels)
        
        #backward and optimizer step
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    if (epoch + 1) % 100 == 0:
        print(f'epoch{epoch+1}/{num_epochs}, loss={loss.item():.4f}')

它起作用了，损失的演变被打印在终端上。谢谢@凤凰！

PS：这是我从以下位置获得此代码的系列视频的链接：Python 工程师的视频（这是 4 部分中的第 4 部分）

Answer 3

只需验证您model返回的内容，它应该是 float类型，即您的outputs 变量否则将其更改为类型我认为您已在前向方法中float
返回类型 int