_conv_ops(x_shape, h_shape, mode)
Find the number of operations required for direct/fft methods of convolution. The direct operations were recorded by making a dummy class to record the number of operations by overriding __mul__
and __add__
. The FFT operations rely on the (well-known) computational complexity of the FFT (and the implementation of _freq_domain_conv
).
Hover to see nodes names; edges to Self not shown, Caped at 50 nodes.
Using a canvas is more power efficient and can get hundred of nodes ; but does not allow hyperlinks; , arrows or text (beyond on hover)
SVG is more flexible but power hungry; and does not scale well to 50 + nodes.
All aboves nodes referred to, (or are referred from) current nodes; Edges from Self to other have been omitted (or all nodes would be connected to the central node "self" which is not useful). Nodes are colored by the library they belong to, and scaled with the number of references pointing them