Ludwig Schubert

I always thought that was intentional to show there was no whitespace on these lines. But reading your issue I realize guides _would_ be more helpful if they worked like...

@brianmorton how would you feel about presenting an interactive list of choices in such cases?

@BadrYoubiIdrissi thank so much for your willingness! I imagine extending the parameterization itself (start at `lucid.optvis.params.images`) will be pretty straightforward, I'm more concerned about e.g. `lucid.optvis.objectives` operating on such a...

Hi @Shulk97 ! Wow, that's quite a PR; so sorry for ignoring it for so long! I'd still be happy to merge all of these, but since I'm about a...

Hi @Shulk97 ! I've run into that issue before; I just wish the bot would point us to the offending commits! (It's likely just a stray email address.) I'll take...

Oh, thanks, I’ll take a look! I had found https://github.com/computationalmodelling/nbval which uses magic comments to to mark cells to be skipped over. I was mostly stuck on how to get...

`image_shape`, `image_value_range`, and `input_name` are all required even in theory. In a nutshell, when lucid imports your model's graph, it needs to replace your model's input (usually a `tf.placeholder`) with...

@tschwabe 's extra step should not be necessary when you tell lucid to use the same input size as you use during training.

Sounds like an exciting application! My Google account is [EDIT]

@ebwendol The specific pre-trained weights we use were trained on that input range. We are not using the weights trained with the slim reimplementation. @colah is currently working on getting...