How to extract saliency map from the ImageNet pretrained with non-RBG input?
N-Jaro opened this issue · comments
Nattapon Jaroenchai commented
I created a model with the non-RGB input, trained it, and saved it in h5 format. I want to get the activation and saliency maps when I predict an input image.
Could anyone please advise how I should proceed with this?
Thanks