Open TerrestrialEclipse opened 3 years ago
Hi @TerrestrialEclipse,
thank you for pointing to this issue. In order to resolve this, I would agree to extend the intermediate format with an additional property for the kernel filtering behaviour, as you proposed in your initial post. This would result in simply setting the new property in the keras frontend and adjusting the backends accordingly.
Keras and Pytorch apply kernels differently:
This could potentially be solved by encoding the intended kernel filtering behavior into the intermediate format. This also involves adapting the backends.