Marco Ancona

The assumption is that all inputs have batch_size as the first dimension of the input tensor. This is what Keras does. As you have a pure TF model, it might...

Looking closer, the current DeepExplain *requires* each input to be at least two-dimensional. A workaround could be to define your second input as having shape [[1]]

I am afraid this is not supported by DeepExplain. The output is expected to be of shape `[batch, n_classes]`. Also, how would that work for image segmentation? Would you generate...

Hello, That check is intended to verify that the batch size is the same. If you have multiple inputs than the len() does not verify the batch size indeed, but...

I have to say that we did not try any time-serie dataset. I would start with the occlusion method, as for 1-D data of shape (2301, 1) that should be...

Hi, positive/negative scores mean positive or negative contributions to the target output, respectively. Your code seems generally correct to me, but I would need to know what is your `xs`...

This does not look like a problem with the library but rather a problem with access to `axes`

Could you please report the error and the code that you are using? Notice that instead of passing `ys` you can mask the target tensor directly (eg. `target = original_target...

Not sure I understand the question here. What takes time is the creation of a new graph with replaced gradients, not the context itself.

Yes, it possible to use an intermediate hidden layer as input to generate attributions (indeed, this is necessary for layers that stop gradient propagation, ie. embedding lookups) You need to...