Pytorch：运行时错误：期望 dtype 为 Float，但得到的是 dtype Long。

Question

在使用Pytorch构建一个简单的神经网络时，我遇到了一个奇怪的错误。我不理解这个错误以及为什么它会涉及到backward函数中的Long和Float数据类型。有没有人遇到过这种情况？感谢任何帮助。

Traceback (most recent call last):
  File "test.py", line 30, in <module>
    loss.backward()
  File "/home/liuyun/anaconda3/envs/torch/lib/python3.7/site-packages/torch/tensor.py", line 198, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph)
  File "/home/liuyun/anaconda3/envs/torch/lib/python3.7/site-packages/torch/autograd/__init__.py", line 100, in backward
    allow_unreachable=True)  # allow_unreachable flag
RuntimeError: expected dtype Float but got dtype Long (validate_dtype at /opt/conda/conda-bld/pytorch_1587428398394/work/aten/src/ATen/native/TensorIterator.cpp:143)
frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x4e (0x7f5856661b5e in /home/liuyun/anaconda3/envs/torch/lib/python3.7/site-packages/torch/lib/libc10.so)
frame #1: at::TensorIterator::compute_types() + 0xce3 (0x7f587e3dc793 in /home/liuyun/anaconda3/envs/torch/lib/python3.7/site
-packages/torch/lib/libtorch_cpu.so)
frame #2: at::TensorIterator::build() + 0x44 (0x7f587e3df174 in /home/liuyun/anaconda3/envs/torch/lib/python3.7/site-packages
/torch/lib/libtorch_cpu.so)
frame #3: at::native::smooth_l1_loss_backward_out(at::Tensor&, at::Tensor const&, at::Tensor const&, at::Tensor const&, long)
 + 0x193 (0x7f587e22cf73 in /home/liuyun/anaconda3/envs/torch/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #4: <unknown function> + 0xe080b7 (0x7f58576960b7 in /home/liuyun/anaconda3/envs/torch/lib/python3.7/site-packages/torc
h/lib/libtorch_cuda.so)
frame #5: at::native::smooth_l1_loss_backward(at::Tensor const&, at::Tensor const&, at::Tensor const&, long) + 0x16e (0x7f587
e23569e in /home/liuyun/anaconda3/envs/torch/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #6: <unknown function> + 0xed98af (0x7f587e71c8af in /home/liuyun/anaconda3/envs/torch/lib/python3.7/site-packages/torc
h/lib/libtorch_cpu.so)
frame #7: <unknown function> + 0xe22286 (0x7f587e665286 in /home/liuyun/anaconda3/envs/torch/lib/python3.7/site-packages/torc
h/lib/libtorch_cpu.so)

以下是源代码：

import torch
import torch.nn as nn
import numpy as np
import torchvision
from torchvision import models
from UTKLoss import MultiLoss
from ipdb import set_trace

# out features [13, 2, 5]
model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 20)
model_ft.cuda()

criterion = MultiLoss()
optimizer = torch.optim.Adam(model_ft.parameters(), lr = 1e-3)

image = torch.randn((1, 3, 128, 128)).cuda()
age = torch.randint(110, (1,)).cuda()
gender = torch.randint(2, (1,)).cuda()
race = torch.randint(5, (1,)).cuda()
optimizer.zero_grad()
output = model_ft(image)
age_loss, gender_loss, race_loss = criterion(output, age, gender, race)
loss = age_loss + gender_loss + race_loss
loss.backward()
optimizer.step()

这是我定义损失函数的方式：

import torch
import torch.nn as nn
import torch.nn.functional as F


class MultiLoss(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, output, age, gender, race):
        age_pred = output[:, :13]
        age_pred = torch.sum(age_pred, 1)
        gender_pred = output[:, 13: 15]
        race_pred = output[:, 15:]
        age_loss = F.smooth_l1_loss(age_pred.view(-1, 1), age.cuda())
        gender_loss = F.cross_entropy(gender_pred, torch.flatten(gender).cuda(), reduction='sum')
        race_loss = F.cross_entropy(race_pred, torch.flatten(race).cuda(), reduction='sum')
        return age_loss, gender_loss, race_loss

- Yun Liu

Answer 1

将criterion函数调用更改为：

age_loss, gender_loss, race_loss = criterion(output, age.float(), gender, race)

如果您查看您的错误，我们可以追溯到：

frame #3: at::native::smooth_l1_loss_backward_out

在MultiLoss类中，smooth_l1_loss函数与age一起使用。因此，在将其传递给criterion时，我将其类型更改为float（因为期望的dtype是Float）。您可以通过打印age.dtype来检查age是torch.int64（即torch.long）。

我这样做后不再出现错误。希望能有所帮助。

- Madhoolika

Answer 2

检查"output"、"age"、"gender"、"race"的数据类型

可能会有如下差异：

"torch.float32" 
"torch.float64"

将它们设置为相同的类型，这将修复错误。

- Abu Bakar Siddik