ONNX loader doesn't load the BatchNorm parameters epsilon and momentum?

[lauracanalini]

To Reproduce
Steps to reproduce the behavior:

1. Load ResNet ONNX here https://drive.google.com/file/d/1gqLI0k4NEQL6dsZFx-iI2zFZBBgucUTd/view?usp=sharing
2. Check values in layers[2]
3. Open ONNX in netron.app
4. Compare values

Expected behavior
They should be the same.

[chavicoski]

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.

eddl/src/serialization/onnx/net/layers/normalization/batchnorm_onnx.cpp

Line 13 in e6de5aa

float epsilon = 1e-05f; // Default value according to ONNX standard

[lauracanalini]

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?

[chavicoski]

Yes, you are right. I am going to change it.

[chavicoski]

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.