output different between onnx and pytorch about onnx HOT 7 CLOSED

cc @justinchuby

from onnx.

Was the model in eval() mode?

from onnx.

Was the model in eval() mode?

yes, in my code, i set model in the eval mode and the fuction result_test in the code what i show above just change to eval model, but the out is also different.

from onnx.

How different are they? Do you have the absolute difference numbers?

from onnx.

Do you have the absolute difference numbers

the difference of input A is:
[[[2.9802322e-08 5.9604645e-08 5.9604645e-08 0.0000000e+00 2.9802322e-08
1.1920929e-07 5.9604645e-08 0.0000000e+00 0.0000000e+00 0.0000000e+00]
[2.0861626e-07 1.7881393e-07 1.7881393e-07 2.3841858e-07 1.6391277e-07
1.1920929e-07 1.7881393e-07 1.1920929e-07 2.3841858e-07 2.3841858e-07]]]

the difference of input B is:
[[[2.5670528e-03 2.4108291e-03 2.4752617e-03 2.3699999e-03 2.5104880e-03
2.3846626e-03 2.3943782e-03 2.5292635e-03 2.3947954e-03 2.4846196e-03]
[3.7431717e-05 1.3673306e-04 9.0770423e-05 1.0877848e-04 2.3484230e-05
1.0919571e-04 1.3816357e-04 1.1563301e-05 1.4400482e-04 9.0532005e-05]]]
i hope the difference will less than 1e-5

from onnx.

Since the error is unlikely due to export errors (judging by the difference above), I suggest creating an issue in the microsoft/onnxruntime repository for further assistance.

from onnx.

Since the error is unlikely due to export errors (judging by the difference above), I suggest creating an issue in the microsoft/onnxruntime repository for further assistance.

ok, thanks a lot

from onnx.