Jacobian mismatch for output 0 with respect to input 0,

[PPPPWU]

Running testcpu File "testcpu.py", line 266, in check_gradient_dconv() File "testcpu.py", line 97, in check_gradient_dconv eps=1e-3)) File "C:\Users\think.conda\envs\snakes\lib\site-packages\torch\autograd\gradcheck.py", line 289, in gradcheck 'numerical:%s\nanalytical:%s\n' % (i, j, n, a)) File "C:\Users\think.conda\envs\snakes\lib\site-packages\torch\autograd\gradcheck.py", line 227, in fail_test raise RuntimeError(msg) RuntimeError: Jacobian mismatch for output 0 with respect to input 0, numerical:tensor([[ 0.0000, 0.0000, -0.3351, ..., 0.0000, 0.0000, 0.0000], [ 0.0000, 0.0421, 0.0000, ..., 0.0000, 0.0000, 0.0000], [ 0.0000, 0.1130, 0.0000, ..., 0.0000, 0.0000, 0.0000], ..., [ 0.0000, 0.0000, 0.0000, ..., 0.0000, 0.0056, 0.0000], [ 0.0000, 0.0000, 0.0000, ..., -0.0942, 0.0010, 0.0000], [ 0.0000, 0.0000, 0.0000, ..., -0.0147, 0.0011, 0.0279]]) analytical:tensor([[ 0.0000, 0.0000, -0.3351, ..., 0.0000, 0.0000, 0.0000], [ 0.0000, 0.0420, 0.0000, ..., 0.0000, 0.0000, 0.0000], [ 0.0000, 0.1130, 0.0000, ..., 0.0000, 0.0000, 0.0000], ..., [ 0.0000, 0.0000, 0.0000, ..., 0.0000, 0.0056, 0.0000], [ 0.0000, 0.0000, 0.0000, ..., -0.0942, 0.0010, 0.0000], [ 0.0000, 0.0000, 0.0000, ..., -0.0147, 0.0011, 0.0279]])

[Sun2018421]

I face the same problem, have u solved it?

[balabooooo]

I have the same problem in ubuntu 22.04.