frederikfaye

What is the structure of the PyPI splinter package?

1

I'm on Ubuntu 16.04 LTS on a 64-bit architecture. It was my understanding that I should be able to install SPLINTER through `pip install splinterpy` (which installs `splinterpy 4.0.4` in...

Where to find implementation of `visualize_class_saliency` and `visualize_regression_saliency`?

2

From https://github.com/raghakot/keras-vis/issues/38#issuecomment-311859428: > `visualize_xxx now has a regression and class variant separated out.` However, nothing like this is in vis/visualization/activation_maximization.py, and in https://github.com/raghakot/keras-vis/blob/668b0e11dab93f3487f23c17e07f40554a8939e9/vis/visualization/saliency.py#L54-L55 it is only referred to, but not...

I'm failing to see the reasoning behind these lines: https://github.com/keras-team/keras-contrib/blob/5ffab172661411218e517a50170bb97760ea567b/keras_contrib/layers/normalization/instancenormalization.py#L80-L81 Say I want to apply an InstanceNormalization layer to tensors all different ranks (e.g. coming from Dense and Conv2D layers),...

Transformed filters count towards learnable parameters

4

I'm puzzled by the number of trainable parameters in networks using `gconv2d`. The script below creates a network using `gconv2d`s from Z2 to C4 to C4 and counts the number...

How to only explain a subset of the input features?

4

I have a CNN model that both take images and scalar variables. I would like to investigate only the importance of the scalars (not the pixels in the image). As...