Raghavendra Kotikalapudi

Thanks, @ahundt. I have been super busy at work lately.

Nope. It's high on my todo list.

+1

I need to update the API. There are a couple of options. 1. You want to visualize attention over all inputs or input at a specific index. 2. Same could...

I have to fix the Readme. For now, the notebook examples are more reliable and correct. I will definitely fix it this weekend.

I am assuming the input is something like `(batchsize, time_dims, input_dims, channels)`. The heatmap will simply be of the same shape which shows how the attention will vary over `time_dims`....

Cool. Looking at it.

Minor update. With `backprop_modifier='relu'` in saliency, you do see something for weak_out. Does it make sense? This is using the deconv approach from matthew ziegler's paper. I am still working...

I was planning on releasing a batch API for the visualizations that would be super fast for use-cases like this. I need to investigate the issue with the leak. Thanks...

We should just fix the issue that causes his use-case to not work. The API should handle N-dim inputs.