Pytorch: RuntimeError:结果类型浮点数不能转换到所需的输出类型Long
Pytorch: RuntimeError:结果类型浮点数不能转换到所需的输出类型Long
提问于 2021-11-25 11:37:52
我有一个模型，看上去如下：
IMG_WIDTH = IMG_HEIGHT = 224
class AlexNet(nn.Module):
def __init__(self, output_dim):
super(AlexNet, self).__init__()
self._to_linear = None
self.x = torch.randn(3, IMG_WIDTH, IMG_HEIGHT).view(-1, 3, IMG_WIDTH, IMG_HEIGHT)
self.features = nn.Sequential(
nn.Conv2d(3, 64, 3, 2, 1), # in_channels, out_channels, kernel_size, stride, padding
nn.MaxPool2d(2),
nn.ReLU(inplace=True),
nn.Conv2d(64, 192, 3, padding=1),
nn.MaxPool2d(2),
nn.ReLU(inplace=True),
nn.Conv2d(192, 384, 3, padding=1),
nn.MaxPool2d(2),
nn.ReLU(inplace=True),
nn.Conv2d(384, 256, 3, padding=1),
nn.MaxPool2d(2),
nn.ReLU(inplace=True),
nn.Conv2d(256, 512, 3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(512, 256, 3, padding=1),
nn.MaxPool2d(2),
nn.ReLU(inplace=True)
)
self.conv(self.x)
self.classifier = nn.Sequential(
nn.Dropout(.5),
nn.Linear(self._to_linear, 4096),
nn.ReLU(inplace=True),
nn.Dropout(.5),
nn.Linear(4096, 4096),
nn.ReLU(inplace=True),
nn.Linear(4096, output_dim),
)
def conv(self, x):
x = self.features(x)
if self._to_linear is None:
self._to_linear = x.shape[1] * x.shape[2] * x.shape[3]
return x
def forward(self, x):
x = self.conv(x)
h = x.view(x.shape[0], -1)
x = self.classifier(h)
return x, h下面是我的优化器和损失函数：
optimizer = torch.optim.Adam(model.parameters())
criterion = nn.BCEWithLogitsLoss().to(device)下面是我的train和evaluate函数：
def train(model, iterator, optimizer, criterion, device):
epoch_loss, epoch_acc = 0, 0
model.train()
for (x, y) in iterator:
# features and labels to the device
x = x.to(device)
y = y.to(device).long()
# Zero the gradients
optimizer.zero_grad()
y_pred, _ = model(x)
# Calculate the loss and accuracy
loss = criterion(y_pred.squeeze(), y)
acc = binary_accuracy(y_pred, y)
# Backward propagate
loss.backward()
# Update the weights
optimizer.step()
epoch_loss +=loss.item()
epoch_acc += acc.item()
return epoch_loss/len(iterator), epoch_acc/len(iterator)
def evaluate(model, iterator, criterion, device):
epoch_loss, epoch_acc = 0, 0
model.eval()
with torch.no_grad():
for (x, y) in iterator:
x = x.to(device)
y = y.to(device).long()
y_pred, _ = model(x)
loss = criterion(y_pred, y)
acc = binary_accuracy(y_pred, y)
epoch_loss += loss.item()
epoch_acc += acc.item()
return epoch_loss/len(iterator), epoch_acc/len(iterator)这是我得到的错误：
RuntimeError: result type Float can't be cast to the desired output type Long什么可能是我的问题，因为我试图将我的标签转换成long张量，如下所示：
y = y.to(device).long()但这似乎行不通。
回答 2
Stack Overflow用户
回答已采纳
发布于 2021-11-26 11:18:16
我在做这件事时遇到了同样的错误：
loss_fn(output, target)其中输出为张量torch.float32 靶为张量torch.int64。解决这个问题的方法是调用这样的损失函数：
loss_fn(output, target.float())Stack Overflow用户
发布于 2022-08-04 14:00:00
我在使用库(Huggingface)时遇到了这个错误。在这种情况下，您无法访问计算损失的代码。不转换传递给库的标签的数据类型。对我有用的是：
labels = labels.astype(np.float32).tolist()页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/70110429
复制相关文章
相似问题
腾讯云开发者
