Quantus

Quantus copied to clipboard

Integrate AutoModelForSequenceClassification through PytorchModel

1

### Description - This PR adds an initial implementation for the HuggingFace SequenceClassification model with some initial functionality. I also organized imports using [isort](https://pypi.org/project/isort/) and made a few adjustments to...

abarbosa94

### Description - Add tabular tests to localisation metrics. ### Minimum acceptance criteria - Specify what is necessary for the PR to be merged with the main branch. - @mentions...

annahedstroem

XAI Inverse Estimation

1

### Description - [x] Docstring fixes in all metrics and fixed typos across code base - [x] Added call_kwargs_che - [x] Replaced assertions for attributions with warnings - [x] InveseEstimation...

annahedstroem

ROAD returns 0 all the time

3

### Description Hello there, as the title says - looks like ROAD returns 0 all the time. In the [one of provided tutorials](https://github.com/understandable-machine-intelligence-lab/Quantus/blob/main/tutorials/Tutorial_ImageNet_Example_All_Metrics.ipynb), the output of ROAD is `0` for...

krebso

Support Model-Agnostic Explainers

1

Hi there, firstly-- kudos for this amazing project :) ### Description of the problem After reviewing the examples and API usage, I understood that I needed to rely on Tensorflow...

abarbosa94

### Description of the problem - Remove dependency of pytest-lazy-fixture which causes problems with pytest==8.0.0 - See problem discussed here: https://github.com/TvoroG/pytest-lazy-fixture/issues/65 Links: - https://docs.pytest.org/en/stable/proposals/parametrize_with_fixtures.html ### Minimum acceptance criteria - Specify...

annahedstroem

### Description - Replace numpy with cupy everywhere ### Minimum acceptance criteria - Specify what is necessary for the PR to be merged with the main branch. - @mentions of...

annahedstroem

Multi-label classification support

1

### Description of the problem - afaik so far, Quantus assumes categorical encoding of `y_batch`, where each input data-point is assigned to exactly 1 label. ### Description of a solution...

aaarrti

The problem faced by GradCAM and Occlusion Sensitivity methods when dealing with images with more than 3 bands.

1

### Description - Imagine we have a task for image classification in the deep learning model that takes a tensor with the shape of m*n*c. Here, m and n are...

BEEILAB

Lime with Relative Input Stability and Local Lipschitz Estimate

1

### Description I have used a tabular dataset "adult census" for my MLP model and wanted to evaluate LIME XAI method with the Quantus metrics. Here is the MLP Model:...

ddurmaz97