RuntimeError: mean(): input dtype should be either floating point or complex dtypes. Got Long instead

Run code ：

import torch
from torch.nn import L1Loss

inputs = torch.tensor([1,2,3])
targets = torch.tensor([1,2,5])

inputs = torch.reshape(inputs,(1,1,1,3))  # 1batch_size,1 individual channel,1 That's ok ,3 Column 
targets = torch.reshape(targets,(1,1,1,3))

loss = L1Loss()
result = loss(inputs,targets)

print(result)

Report errors RuntimeError: mean(): input dtype should be either floating point or complex dtypes. Got Long instead.

The code that went wrong ：

inputs = torch.tensor([1,2,3])
targets = torch.tensor([1,2,5])

Change data type

inputs = torch.tensor([1,2,3],dtype=torch.float32)
targets = torch.tensor([1,2,5],dtype=torch.float32)

Run again ：