I currently work on building ResNet for Loihi by using NengoDL converter and NengoLoihi with reference to the tutorial of “Converting a Keras model to an SNN on Loihi (https://www.nengo.ai/nengo-loihi/examples/keras-to-loihi.html).”
The ResNet has the Conv2D with ‘same’ padding, but it seems the Conv2D with ‘same’ padding is not supported by NengoLoihi. When I attempted to run a part of ResNet, I got the following message:
“NotImplementedError: nengo-loihi only supports convolution with ‘valid’ padding.”
Has anyone implemented the ResNet on Loihi by using NengoDL converter and NengoLoihi? And, if the Conv2D with ‘same’ padding cannot be used, the outputs of the the Conv2D are shrunk. Are there solutions to avoid it?