Closed lauracanalini closed 2 years ago
They are almost the same, there is a certain loss of precision.
Reproducing the issue: Netron: momentum = 0.009999999776482582 - EDDL momentum = 0.01 Netron: epsilon = 0.10000000149011612 - EDDL epsilon = 0.1
And they must be loaded because the default values in ONNX are momentum=0.9 and epsilon=1e-5.
Right, I was loading the ONNX incorrectly.
But now I have another question: if as reported issue #302, eddl uses 1 - momentum
compared to PyTorch, when it loads a PyTorch ONNX shouldn't it load 1 - onnx momentum
?
Yes, you are right. I am going to change it.
I checked the ONNX operators definition and it is correct now, I don't have to change it.
You can see here that the ONNX definiton uses the momentum like the EDDL. This means that if you use a momentum of 0.1 in Pytorch, It should export it as momenum=0.9. But the EDDL is importing it right.
To Reproduce Steps to reproduce the behavior:
layers[2]
Expected behavior They should be the same.