when i run python testcpu.py,i get some UserWarning messages as following.

[Sun2018421]

Whe i run python testcpu.py, and i have the result as following. I wonder that the result is right? or something is wrong during I run the code.

torch.Size([20, 32, 7, 7])
torch.Size([20, 32, 7, 7])
torch.Size([20, 32, 7, 7])
0.971507, 1.943014
0.971507, 1.943014
Zero offset passed
/home/sxf/.conda/envs/dcnv2/lib/python3.6/site-packages/torch/autograd/gradcheck.py:633: UserWarning: Input #0 requires gradient and is not a double precision floating point or complex. This check will likely fail if all the inputs are not of double precision floating point or complex. 
  f'Input #{idx} requires gradient and '
/home/sxf/.conda/envs/dcnv2/lib/python3.6/site-packages/torch/autograd/gradcheck.py:633: UserWarning: Input #2 requires gradient and is not a double precision floating point or complex. This check will likely fail if all the inputs are not of double precision floating point or complex. 
  f'Input #{idx} requires gradient and '
check_gradient_dpooling: True
/home/sxf/.conda/envs/dcnv2/lib/python3.6/site-packages/torch/autograd/gradcheck.py:633: UserWarning: Input #1 requires gradient and is not a double precision floating point or complex. This check will likely fail if all the inputs are not of double precision floating point or complex. 
  f'Input #{idx} requires gradient and '
/home/sxf/.conda/envs/dcnv2/lib/python3.6/site-packages/torch/autograd/gradcheck.py:633: UserWarning: Input #3 requires gradient and is not a double precision floating point or complex. This check will likely fail if all the inputs are not of double precision floating point or complex. 
  f'Input #{idx} requires gradient and '
/home/sxf/.conda/envs/dcnv2/lib/python3.6/site-packages/torch/autograd/gradcheck.py:633: UserWarning: Input #4 requires gradient and is not a double precision floating point or complex. This check will likely fail if all the inputs are not of double precision floating point or complex. 
  f'Input #{idx} requires gradient and '
check_gradient_dconv:  True