RuntimeError: Jacobian mismatch for output 0 with respect to input 1,

[dk-liang]

When I run python test.py

torch.Size([2, 64, 128, 128])
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/dkliang/miniconda3/envs/pytorch1.2/lib/python3.6/site-packages/torch/autograd/gradcheck.py:242: UserWarning: At least one of the inputs that requires gradient is not of double precision floating point. This check will likely fail if all the inputs are not of double precision floating point.
'At least one of the inputs that requires gradient '
check_gradient_dpooling: True
Traceback (most recent call last):
File "test.py", line 265, in
check_gradient_dconv()
File "test.py", line 97, in check_gradient_dconv
eps=1e-3, atol=1e-4, rtol=1e-2))
File "/home/dkliang/miniconda3/envs/pytorch1.2/lib/python3.6/site-packages/torch/autograd/gradcheck.py", line 289, in gradcheck
'numerical:%s\nanalytical:%s\n' % (i, j, n, a))
File "/home/dkliang/miniconda3/envs/pytorch1.2/lib/python3.6/site-packages/torch/autograd/gradcheck.py", line 227, in fail_test
raise RuntimeError(msg)
RuntimeError: Jacobian mismatch for output 0 with respect to input 1,
numerical:tensor([[-0.0003, 0.0000, 0.0000, ..., 0.0000, 0.0000, 0.0000],
[ 0.0000, 0.0013, 0.0000, ..., 0.0000, 0.0000, 0.0000],
[ 0.0000, 0.0000, 0.0000, ..., 0.0000, 0.0000, 0.0000],
...,
[ 0.0000, 0.0000, 0.0000, ..., 0.0000, 0.0000, 0.0000],
[ 0.0000, 0.0000, 0.0000, ..., 0.0000, 0.0000, 0.0000],
[ 0.0000, 0.0000, 0.0000, ..., 0.0000, 0.0000, 0.0000]])
analytical:tensor([[-0.0003, 0.0000, 0.0000, ..., 0.0000, 0.0000, 0.0000],
[ 0.0000, 0.0013, 0.0000, ..., 0.0000, 0.0000, 0.0000],
[ 0.0000, 0.0000, 0.0000, ..., 0.0000, 0.0000, 0.0000],
...,
[ 0.0000, 0.0000, 0.0000, ..., 0.0000, 0.0000, 0.0000],
[ 0.0000, 0.0000, 0.0000, ..., 0.0000, 0.0000, 0.0000],
[ 0.0000, 0.0000, 0.0000, ..., 0.0000, 0.0000, 0.0000]])

[Mukosame]

Hi @dk-liang , please refer https://github.com/CharlesShang/DCNv2#known-issues

In summary, it's not a problem.