Verena Praher

Hi, I tried to run the example from the README.md and I run into the following issues: * `grad_rollout = VITAttentionGradRollout(model, discard_ratio=0.9, head_fusion='max')` causes ` TypeError: __init__() got an unexpected...

Mismatch between the ImageNet-A classes reported in the paper and in the download?

1

Hi, thanks for providing this dataset! I downloaded ImageNet-A following the link in the README of this repository and had a look at the provided README to see which classes...

Errors with explaining images

1

Hi Thomas, recently I have been trying to use lime for images but I always get an error message (and since yesterday it's two different ones). Both errors came after...

Confusion when using class ChordEvaluation

2

### Expected behaviour When looking at the [docs for `ChordEvaluation`](https://madmom.readthedocs.io/en/latest/modules/evaluation/chords.html#madmom.evaluation.chords.ChordEvaluation) I expected that I need to pass the file paths to the annotation and prediction files. The doc says: ```...

Hi everyone, thanks for this great paper, I am really looking forward to using TCAV for my own research. Currently I am trying to make sense of the experiment described...

Version mismatch between library and pretrained model?

3

**Describe the bug** I installed the most recent `nussl` version (1.1.3) using pip today and tried to run the Deep Clustering example, which first downloads the model `dpcl-wsj2mix-model.pth`. This is...

How to use pretrained models

2

**You question here** I don't understand how the [pretrained models](http://nussl.ci.northwestern.edu/) (e.g. musdb+slakhv0_TG3EvX6.pth) should be used. What is the model class for each of the models (I can only see that...

Random train sample in s_test

4

Hi, I was wondering why you are taking a random training sample in `s_test`. And according to the comment `TODO: do x, t really have to be chosen RANDOMLY from...

Passing config['test_start_index'] to calc_grad_z

2

Hi, I am not sure if I am misunderstanding the parameter or if it shouldn't be passed to `calc_grad_z`: https://github.com/nimarb/pytorch_influence_functions/blob/4df5d2ec1baae38d70345740b7eca7466e3b48ef/pytorch_influence_functions/calc_influence_function.py#L111 I assumed it should loop over the whole training set....

UI elements with matlab_kernel

4

Hi, is it possible to have UI elements (maybe through widgets) with a MATLAB kernel? I have googled a lot but I could not find any answer. I would also...