Thank you for this useful visualization package!
Right now I have a two-input, one-output model as follows
I am using GradCAM, with code snippet below. I have stated my penultimate layer to be 'ria-conv', which happens after concatenation of both networks.
However, the dimension of cam is 2 - one for each network (15 * 256 * 320 is my image count * image dimensions) , as shown in this screenshot
As far as my understanding goes, since the actual last convolutional layer is after concatenation, cam should be 1 * 15 * 256 * 320? This happens both when I explicitly state the penultimate layer and when I state it as -1.
Thank you for this useful visualization package!
Right now I have a two-input, one-output model as follows
I am using GradCAM, with code snippet below. I have stated my penultimate layer to be 'ria-conv', which happens after concatenation of both networks.
However, the dimension of
camis 2 - one for each network (15 * 256 * 320 is my image count * image dimensions) , as shown in this screenshotAs far as my understanding goes, since the actual last convolutional layer is after concatenation,
camshould be 1 * 15 * 256 * 320? This happens both when I explicitly state the penultimate layer and when I state it as -1.