conv – Convolution¶
Note
Two similar implementation exists for conv2d:
signal.conv2dandnnet.conv2d.
The former implements a traditional 2D convolution, while the latter implements the convolutional layers present in convolutional neural networks (where filters are 3D and pool over several input channels).
-
conv.fft(*todo)¶ [James has some code for this, but hasn’t gotten it into the source tree yet.]