TF-Explain support for multi input model which take image and text as input for classification task
harsha89 opened this issue · 1 comments
harsha89 commented
Hi,
Thank you for the awesome work on the module.
I have a requirement of visualizing grad cam for multi input model which take image and text as input. This grad cam is specific to the image input of the multi modal tensorflow network architecure.
Since two models concatenate at the end, how should I select the last layer or how gradients can flow through concatenation layer? Any input is highly welcome.
Thanks,
Harsha
harsha89 commented
I have found the solution. Hence closing the issue.