neural-api
neural-api copied to clipboard
Add kEffNet 1.0 building block.
Add kEffNet 1.0 building block described on the paper "Grouped Pointwise Convolutions Significantly Reduces Parameters in EfficientNet".
Just curious. Is the kEffNet building block capable of adding a 1D signal or is the convolution always 2D?
Good question. This building block is described in these 2 papers:
- Grouped Pointwise Convolutions Significantly Reduces Parameters in EfficientNet.
- Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks.
If your input has the 1x1xC shape (C is the number of channels), you can use this building block replacing dense layers.