Hi @fitushar
Thank you for sharing such great repo.But when I run this program using my own data set and weights,I get the following error:

At the same time,Grad-CAM and Overlay cannot be displayed successfully,the results are shown below:

I printed the gradients and found that they were all 0.

I don't know what's wrong. Could you please give me some help?
Looking forward to your reply.
Thanks in advance.

Best.

Hello,

I took a quick look into the code and found your data in "nii.gz" format, but I assume it is still taken as images (height, width, channels) by the model right? I don't have much knowledge regarding biomedical imaging tho..

Could this script be used for video analysis? I fed my 3D CNN with video data, which has the dimension of time.

Hello, do you know where I can find the dataset? what type of input dataset which you are using? Thank you.

Hi,

I'm looking to apply Grad-CAM to a 3D CNN classifier that I have trained.
This CNN takes input volumes of shape (250,250,6). I have applied the same approach as outlined in Grad-CAM.ipynb to this network.

A heatmap of the correct shape is returned. However, I'm finding that only 4 of those heatmap slices are unique.

i.e.

heatmap[ : , : , 0 ] == heatmap[ : , : , 1 ]

and

heatmap[ : , : , 4 ] == heatmap[ : , : , 5 ]

I was wondering if you had come across this before or have any idea what could be going on.

Thank you,
James.