RuntimeError: “max_pool2d“ not implemented for ‘Long‘

Sample code ：

import torch
#  The input image (5X5)
from torch import nn
from torch.nn import MaxPool2d

# RuntimeError: "max_pool2d" not implemented for 'Long'  This error is a data type error , So we need a input Add a data type restriction 
input = torch.tensor([[1,2,0,3,1],
                      [0,1,2,3,1],
                      [1,2,1,0,0],
                      [5,2,3,1,1],
                      [2,1,0,1,1]])


#  from [ Official documents ](https://pytorch.org/docs/stable/generated/torch.nn.MaxPool2d.html#torch.nn.MaxPool2d) Given API You can know the details of use   requirement   The input of is four-dimensional 

# (batch_size,channels,H,W)=(-1,1,5,5) The first one is -1  to -1 Is to let him calculate batch_size
input = torch.reshape(input,(-1,1,5,5))

print(input.shape)

#  Building neural networks 
class Booze(nn.Module):

    #  Inherit nn.Module The initialization 
    def __init__(self):
        super(Booze, self).__init__()
        self.maxpool1 = MaxPool2d(kernel_size=3,ceil_mode=True)

    #  rewrite forward function 
    def forward(self,x):
        output = self.maxpool1(x)
        return output

obj = Booze()
output = obj(input)
print(output)

An error occurs when running this code ：RuntimeError: "max_pool2d" not implemented for 'Long'.

This error is a data type error , So we have to deal with this input Add a data type restriction .
The problem code is

input = torch.tensor([[1,2,0,3,1],
                      [0,1,2,3,1],
                      [1,2,1,0,0],
                      [5,2,3,1,1],
                      [2,1,0,1,1]])

This code . Put data type restrictions on it dtype=torch.float32. I'll change it to

input = torch.tensor([[1,2,0,3,1],
                      [0,1,2,3,1],
                      [1,2,1,0,0],
                      [5,2,3,1,1],
                      [2,1,0,1,1]],dtype=torch.float32)

Run the result again and no error will be reported .