The function [`convole2NN`](http://arrayfire.org/docs/group__signal__func__convolve2.htm#ga8a6da9b0bf8e0287d71d02e2cd763cde) does not allow for any of the of the values of the `padding` parameter to be 0. It is relatively common practice to use 0 padding in convolutional layers. Is this an oversight or a decision? If a decision, why?
The function
convole2NNdoes not allow for any of the of the values of thepaddingparameter to be 0.It is relatively common practice to use 0 padding in convolutional layers.
Is this an oversight or a decision? If a decision, why?