dnnviewer
dnnviewer copied to clipboard
Input * Weight contribution graph
Given a neural unit of a Dense layer, given an input sample (image), display the bar chart of the products of the weight times the input as a new tab in the unit quadrant
Main issue is the when and where to compute the activation map since it is used in two locations (two bottom right quadrants) and it requires quite large computation such that we want to avoid doubling it.