Open sodaGH opened 6 years ago
I would also be interested in whether this can be used for 3D inputs.
I think the direct cause of the error has already been corrected in current master branch. But, the problem I wrote in issues#113 also occurs here. If you are using Conv2D, please execute the step in issue#113.
I am having the same issue. I have a 3D VGG. Saliency Maps are generated by visualize_cam doesnt work.
@jalilahmed , Can I see the error log of your issue ?
@keisen The library was NOT UPDATED. Doing an UPDATE removed the error. Thanks for your quick response.
Thanks for your great work! I want to visualize the grad-CAM figure for my 3D data image. However, I met some problem at this line:
grads = visualize_cam(model, layer_idx, filter_indices=20, seed_input=img, backprop_modifier=modifier)
in the code block:It returns the error:
My data size is 49-41-40, and I succeed in drawing the saliency figure. Do you know how to fix this problem? Thanks for your reading! And looking forward to your reply.