Quantus

Quantus copied to clipboard

Hi! Thanks alot again for this inpiring package! ### Description of the problem I was trying to pre-compute softmax-attributions `quantus.explain` and evaluate them on a list of metrics through `quantus.evaluate`,...

vedal

### Description - The codecov badge is correctly pointing the user to the report but it does not capture the coverage % but states unknown ### Steps to reproduce the...

annahedstroem

Adding "true" batch implementation to metrics

4

Hey @annahedstroem , Thank you for creating such an excellent library. I've been using it extensively in my recent research, and it's been incredibly helpful. While working with the library,...

davor10105

### Description ``` >>> python3.9 -m venv venvs/testenv >>> source venvs/testenv/bin/activate >>> pip install git+https://github.com/understandable-machine-intelligence-lab/Quantus.git # succesfully installs >>> import quantus Traceback (most recent call last): File "", line 1,...

annahedstroem

### Description of the problem - Many Quantus metrics practically work with non "feature importance" explanations (i.e., can accept free form explaantions ### Description of a solution 1. Remove unnecessary...

annahedstroem

quanda link in README.md

1

### Implemented changes - Added a **quanda** link to README.md - Changed pytest.ini configuration to ignore FutureWarning due to failing tests

dilyabareeva

Batched metrics

11

### Description - Implementing true batch processing for the available metrics - This follows the previously raised [issue](https://github.com/understandable-machine-intelligence-lab/Quantus/issues/350). - The improvements gained from the batched processing seem to hover at...

davor10105

- If I want to apply it in a customized method - I want the pseudo code or the general scheme for this purpose - Would You Please guide me...

soumiadjellikh

Sensitivity-n seems to average over features and correlate samples rather than correlate features and average over samples

4

Hello @annahedstroem, It is possible that I am confusing something or calling the function incorrectly but if not, then I think there might be a mistake in how Sensitivity-n is...

arnon-1

**Description:** I encountered a `ValueError` when running the `FaithfulnessCorrelation` metric in Quantus. The error message indicates that `subset_size` must be smaller than the input size, but even after setting it...

officialarijit