Note
Two similar implementation exists for conv2d:
signal.conv2d and nnet.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).
signal.conv.conv2d performs a basic 2D convolution of the input with the given filters. The input parameter can be a single 2D image or a 3D tensor, containing a set of images. Similarly, filters can be a single 2D filter or a 3D tensor, corresponding to a set of 2D filters.
Shape parameters are optional and will result in faster execution.
Parameters: |
|
---|---|
Return type: | symbolic 2D,3D or 4D tensor |
Returns: | tensor of filtered images, with shape ([number images,] [number filters,] image height, image width) |
[James has some code for this, but hasn’t gotten it into the source tree yet.]