Conv performs convolution of filter over img into out.

Conv1 performs convolution of single filter over img into out.

ConvDiff computes difference of two separate filter convolutions (fltOn - fltOff) over two images into out.

Deconv performs reverse convolution of filter -- given output of filter, accumulates an input image as sum of filter * output activation.

EdgeAvg returns the average value around the effective edge of image at padWidth in from each side.

FadePad fades given padding width of float32 image around sides gradually fading the edge value toward a mean edge value.

FadePadRGB fades given padding width of float32 image around sides gradually fading the edge value toward a mean edge value.

FeatAgg does simple aggregation of feature rows from one feature map to another.

GreyTensorToImage converts a greyscale tensor to image -- uses existing img if it is of correct size, otherwise makes a new one.

LeftHalf returns the left / top half of a filter.

MaxPool performs max-pooling over given pool size and spacing.

MaxReduceFilterY performs max-pooling reduce over inner Filter Y dimension (polarities, colors) must have shape: Y, X, Polarities, Angles.

OuterAgg does simple aggregation of outer-most dimension from tensor into another 4D tensor, with Y, X as outer-most two dimensions, starting at given inner-most feature offset, and inner row-wise offset.

RGBTensorToImage converts an RGB etensor to image -- uses existing image if it is of correct size, otherwise makes a new one.

RGBToGrey converts an RGB input image to a greyscale etensor in preparation for processing.

RGBToTensor converts an RGB input image to an RGB etensor with outer dimension as RGB components.

TensorLogNorm32 computes 1 + log of all the numbers and then does Max Div renorm so result is normalized in 0-1 range.

TensorLogNorm64 computes 1 + log of all the numbers and then does Max Div renorm so result is normalized in 0-1 range.

UnPool performs inverse max-pooling over given pool size and spacing.

WrapPad wraps given padding width of float32 image around sides i.e., padding for left side of image is the (mirrored) bits from the right side of image, etc.

WrapPadRGB wraps given padding width of float32 image around sides i.e., padding for left side of image is the (mirrored) bits from the right side of image, etc.

the commit JUST BEFORE the release.

UTC.

Geom contains the filtering geometry info for a given filter pass.