Initialize GradCAM mask summation with zeros.

[nalinimsingh]

From my read of the GradCAM paper, this matrix should be initialized with zeroes, so that cam contains only the weighted sum of the entries in outputs. Feel free to correct me here if I'm misinterpreting anything!

[This doesn't affect the qualitative trend you see across the image in any of the generated GradCAM masks, since this is a constant shift at each pixel, but it does slightly perturb some of the numeric values.]

[potocpav]

For VGG it doesn't matter, but for my network, this change was necessary to get meaningful results. It is indeed the correct approach.

[nalinimsingh]

@jacobgil Friendly ping -- are you able to review this?

[habibrostami]

I have a model with excellent accuracy an Roc but heat map generated by using grad cam is not reasonable? I used a architecture contains dome conv and batch normalizatio. Thank you