Recent Releases of quantus
quantus - v0.6.0
v0.6.0
This release introduces a major update to Quantus, focused on performance, scalability, and compatibility with the key addition being the support for batched metric evaluation, which significantly improves runtime efficiency. The release also includes initial support for HuggingFace models, internal cleanups, and compatibility upgrades.
What’s Changed
Batch support for explanation metrics
- Added batch-based evaluation to the following metrics:
PixelFlipping,Monotonicity,MonotonicityCorrelation,FaithfulnessCorrelation,FaithfulnessEstimate.
- Utility functions adapted for batch computation:
correlation_pearson,correlation_spearman,correlation_kendall_tausimilarity,calculate_auc,get_baseline_dict.
- Legacy per-instance versions removed for consistency and runtime gains.
Batch correctness was validated via side-by-side comparison with previous outputs across 30 random runs per sample. Deterministic metrics were verified using np.allclose, while stochastic ones were compared using statistical tests (e.g., t-tests showed strong output agreement in >90% of cases).
Thanks to @davor10105 for leading the batch refactor and validation.
HuggingFace Transformers support
- Initial integration of
transformersviaPyTorchModelwrapper forSequenceClassificationtasks. predictnow handles HuggingFace models out of the box.- Added test coverage and linting via
toxandflake8.
Thanks to @abarbosa94 for the transformer implementation.
Other improvements
- Dropped Python 3.7 support.
- Cleaned up
pyproject.toml; improved linting and module verification (mypy,flake8,isort). - Fixed
normalise_func_kwargsbug inbase.py. - Resolved shape mismatch in Region Perturbation visualisations for batched inputs (#353).
- Updated documentation and README links (e.g., QUANDA references).
- Jupyter Notebook
Published by annahedstroem 7 months ago
quantus - v0.5.3
What's Changed
- Bugfix: Added explainfunckwargs to SmoothMPRT and zennit tests by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/318
- Improvement: Add warning of deprecated argument (handle elegantly) by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/319
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.5.2...v0.5.3
- Jupyter Notebook
Published by annahedstroem about 2 years ago
quantus - v0.5.2
What's Changed
- Fixing indent bug in metrics by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/316
- New release 0.5.2 bugfix by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/317
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.5.1...v0.5.2
- Jupyter Notebook
Published by annahedstroem about 2 years ago
quantus - v0.5.1
What's Changed
- Bug fixes for the
EfficientMPRTmetric and expand quantus.evaluate func by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/314 - Update
pandasversion control (to work smoothly withColabenvironment) and add back print warn message for Model Parameter Randomisation Test by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/315
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.5.0...v0.5.1
- Jupyter Notebook
Published by annahedstroem over 2 years ago
quantus - v0.5.0
What's Changed
In this release, we introduce two new metrics, SmoothMPRT and EfficientMPRT, which are variants of the Model Parameter Randomisation Test (MPRT). These implementations are from the paper "Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test " by Hedström et al., 2023 published at NeurIPS XAIA.
- Unifying PR release v0.4.5 by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/307
- MPRT metrics: EfficientMPRT and SmoothMPRT by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/308
- Smaller fixes:
- @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/312
- @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/313
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.4.5...v0.5.0
- Jupyter Notebook
Published by annahedstroem over 2 years ago
quantus - v0.4.5
What's Changed
- Unify metric API by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/294
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.4.4...v0.4.5
- Jupyter Notebook
Published by annahedstroem over 2 years ago
quantus - v0.4.4
What's Changed
- Remove redundant attributes_check by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/287
- Resolve softmax issues with pytorch_model.py by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/283
- Fix channels first issue by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/305
- New release 0.4.4 by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/306
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.4.3...v0.4.4
- Jupyter Notebook
Published by annahedstroem over 2 years ago
quantus - v0.4.3
What's Changed
- Fixing https://github.com/understandable-machine-intelligence-lab/Quantus/issues/292
- Fixes on v0.4.2 by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/291
- dynamic version fix by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/293
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.4.2...v0.4.3
- Jupyter Notebook
Published by annahedstroem over 2 years ago
quantus - v0.4.2
What's Changed
- More exposure to quantum functionality including
modelandutils - Create transparency with respect to the metric’s data and model applicability by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/279
- Update evaluation.py by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/282
- Fixed issue in max_sensitivity.py by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/289
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.4.1...v0.4.2
- Jupyter Notebook
Published by annahedstroem over 2 years ago
quantus - v0.4.1
What's Changed
- Review distance metrics and added squared distance as measure by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/264
- Update requirements_test.txt by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/266
- Add py.typed by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/269
- Toml + Tox Migration by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/270
- update README.md by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/278
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.4.0...v0.4.1
- Jupyter Notebook
Published by annahedstroem over 2 years ago
quantus - v0.4.0
What's Changed
- Fix warnperturbationcausednochange by @p-wojciechowski in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/250
- Packaging by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/256
- Add 3.10 and 3.11 Python support
- Clean-up requirements_test.txt
- Update
torch,tensorflowversions and fixingprotobufincompatibility - Check that optional dependencies packages in
setup.pyare the same as inrequirements_test.txt - Clean-up
setup.py, including adding required and removing unnecessary imports - Clean-up
pytests
- Setuptools-bug fixed, extra_requires not correctly identified by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/258
- Updated python publish script by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/259
- Python package bug by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/260
- Updated setup.py with absolute path by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/262
- Add reqs via MANIFEST.ini by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/263
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.3.5...v0.4.0
- Jupyter Notebook
Published by annahedstroem almost 3 years ago
quantus - v0.3.5
What's Changed
- #195 fix autodoc for special members by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/239
- #219 fix unstable tests by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/241
- Added implementation and tests for return_aggregate=True for BatchedMetric by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/244
- Action fixes by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/246
- Fix bugs and provide flexibility for Softmax argument by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/230
- Tutorial addition and resolving fixture by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/245
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.3.4...v0.3.5
- Jupyter Notebook
Published by annahedstroem almost 3 years ago
quantus - v0.3.4
What's Changed
- Add tests for tabular (2D) data by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/218
- Fixed TF explain bug by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/231
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.3.3...v0.3.4
- Jupyter Notebook
Published by annahedstroem about 3 years ago
quantus - v0.3.3
What's Changed
- Updated contact details by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/226
- Issue 199 by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/214
- Fix minor misleading error message in Robustness metrics by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/227
- Input Invariance Metric (issue 169) by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/225
- exposed constants to user by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/228
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.3.2...v0.3.3
- Jupyter Notebook
Published by annahedstroem about 3 years ago
quantus - v0.3.2
What's Changed
- Added first draft of normalisebyaveragesecondmoment_estimate by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/197
- Use mini batch for tests by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/198
- TF model refactorings by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/209
- Feature/relative stability metric by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/210
- Issue 122 by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/205
- add new methods to captum and tf-explain funcs by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/206
- Fixing issue with bluratindices (Issue #200) by @leanderweber in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/208
- Fix IROF metric - perturbation accumulation and counting the segments by @p-wojciechowski in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/221
New Contributors
- @p-wojciechowski made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/221
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.3.1...v0.3.2
- Jupyter Notebook
Published by annahedstroem about 3 years ago
quantus - v0.3.1
What's Changed (smaller PRs)
- Improve error message by @vedal in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/185
- Default value of explainfunckwargs cannot be unpacked. by @vedal in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/184
- Added AUC calculation to Pixel-Flipping by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/189
- Docs by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/190
- #173 Fix GitHub heatmaps by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/188
- Validate predictions change robustness by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/183
- Citation fixes by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/192
- Update requirements_test.txt by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/193
- Tutorial fixes by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/194
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.3.0...v0.3.1
- Jupyter Notebook
Published by annahedstroem over 3 years ago
quantus - v0.3.0
What's Changed
Bigger PRs
- Refactor
custom_preprocess()for more robustness by @dkrako, reviewed by @annahedstroem, @leanderweber in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/167- Make the implementation
custom_preprocess()more flexible: instead of passing the complete tuple withmodel, x_batch, y_batch, a_batch, s_batch, ..we instead pass a dictionary with the variable names as keys.
- Make the implementation
- Batched evaluation by @dkrako, reviewed by @annahedstroem, @leanderweber in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/168
- This PR implements the classes BatchedMetric and BatchedPerturbationMetric
- This is a rewrite of this PR: https://github.com/understandable-machine-intelligence-lab/Quantus/pull/87
- It solves the following issue: https://github.com/understandable-machine-intelligence-lab/Quantus/issues/80
- This will speed up a lot of metrics.
- Not all metrics in Quantus are yet updated with BatchedPerturbationMetric. The efforts of deploying this new construct with more metrics for efficiency gains will continue.
- Change normalisation default, fix bug in normalisebynegative, adapt citations, absolute imports by @leanderweber, reviewed by @annahedstroem, @dkrako in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/166
- Make some Updates to the readthedocs
- Update and Unify Citations in all Metrics
- Update, unify, and sort all imports
- Change all relative imports to absolute
- Rethink star imports. Specifically, restructure helpers to distinguish internal functions and functions that should be user-accessible.
- Change the normalisationfunc default to normalisebymax instead of normaliseby_negative due to the latter treating pos/neg values differently
- Target some bugs within the normalisation functions and their application
- Merge installation options rework (see PR https://github.com/understandable-machine-intelligence-lab/Quantus/pull/172)
- Updated and cleaned-up README.md file
- Mypy: fix errors fix by @dilyabareeva, reviewed by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/171
- An in-depth look at the typing, branched from mypy-static-type-checker
- Fix errors or reject with reason
Smaller PRs
- Installation option refactoring to be more concise by @leanderweber, reviewed by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/172
- Refactored installation options, e.g., "extras" removed, instead singular XAI libraries are targetable.
- Updated Quantus package dependencies
- Bugfixes to Installation and Tutorials by @leanderweber, reviewed by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/176
- Tabular data minimal example by @dilyabareeva, reviewed by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/175
- Jupyter notebook/ tutorial based on Titanic data, showing with a minimal example how to use Quantus
- Add time series tutorial by @dkrako, reviewed by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/177
- Remove coverage>=6.2 by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/179
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.2.2...v0.3.0
- Jupyter Notebook
Published by annahedstroem over 3 years ago
quantus - v0.2.2
What's Changed 🚀
Bigger PRs:
- Fixes, license, readthedocs and docstrings by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/156
- Removed coverage from requirements.txt
- Finished all docstrings accordingly to numpydoc
- Included API documentation
- Configured readthedocs.org
- Added license stubs to all src files
- Added codecov badge
- Added assumptions on data applicability
- Removed * imports
- Fixes and enhancements tutorials, other fixes to tests, .gitignore and README.md by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/164
- Added ImageNet data as examples
- Tutorials clean-up and added data to assets
- Fixed all tutorials, removed colab dependency and simplified install
- Updated .gitignore
- Replaced an assert with a warning
- Moved PR template
- Cleaned up assets folder
- Removed term_color
- Updated docs, post-tutorial API docs fixes
Smaller PRs:
- 146 treatment of slices in baseline replacement by indices is wrong by @leanderweber in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/148
- Require
numpy>=1.19.5for correct version solving by @vedal in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/151 - Code formatting and documentation by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/154
- bug: tensorflow is required, even if not used by @vedal in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/158
- Create pullrequesttemplate.md by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/161
- Create issue templates by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/160
- CONTRIBUTING.md by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/157
- Fixing indentation of LLE metric by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/162
- Create python-publish.yml by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/163
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.2.1...v0.2.2
- Jupyter Notebook
Published by annahedstroem over 3 years ago
quantus - v0.2.1
Minor fixes
- Merge branch 'main' into 146-treatment-of-slices-in-baseline_replacem…
- Merge pull request
- Fixed bug Relevance Rank Accuracy - reversed line 140 to earlier vers…
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.2.0...v0.2.1
- Jupyter Notebook
Published by annahedstroem over 3 years ago
quantus - v0.2.0
What's Changed 🚀
For more transparent kwargs-passing and error handling, we have updated the API of Quantus! The main changes are the following:
- Add function-specific keyword-arguments to metric functions. by @dkrako in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/124
From implicit to explicit argument passing. To mitigate the risk of user typos and other undefined behaviours, the new version 0.2.0 forces explicit argument passing of all metric initalisations and calls. Instead of passing all evaluation parameters in one single kwargs list, e.g.,
python
kwargs = {"n_perturb_samples": 10, "abs": False, "normalise": True, "explain_func": quantus.explain, method: "Saliency"}}
metric = Infidelity(**kwargs)
metric(model=model, x_batch=x, y_batch=y, a_batch=a, s_batch=s, **kwargs)
which could for example result in typos being overlooked, we now separate the parameters into different dictionaries such as normalise_func_kwargs, explain_func_kwargs, model_predict_kwargs. With the new API, the same call looks like this:
python
metric = Infidelity(n_perturb_samples=10, abs=False, normalise=True)
metric(model=model, x_batch=x, y_batch=y, a_batch=a, s_batch=s, explain_func=quantus.explain, explain_func_kwargs={"method": "Saliency"})
In this way, we assert better control over the parameters. If an unexpected argument is passed, an error will now be thrown.
Extended the base.Metric class. Many metrics share the same logic when it comes to general attributes and pre-processing. To remove duplicate code, we extended the base class, which now includes some key methods general_preprocessing, custom_preprocessing, evaluate_instance, custom_postprocessing all which could be used for various Metric implementations.
Additional functionality in helpers and increased general code-quality. We have shortended and rewritten scripts where necessary for better code readability. Added new functions and refactored existing ones to adhere to PEP-8.
If these API changes are not suitable for your project's needs, please install a previous release version such as v0.1.6 via:
bash
pip install quantus==0.1.6
Also, a minor PR was incorporated:
- Use auto.tqdm by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/143
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.1.6...v0.2.0
- Jupyter Notebook
Published by annahedstroem over 3 years ago
quantus - v0.1.6
v0.1.6 - A new release 💥
What's Changed
- Fixed a bug with patch creation and with .index() on np arrays by @leanderweber in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/140
- Do not show zennit warning, if captum or tf-explain is used by @aaarrti in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/141
- Create CITATION
- Fixed bug uniform sampling (str) option in getbaselinedict
New Contributors
- @aaarrti made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/141
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.1.5...v0.1.6
- Jupyter Notebook
Published by annahedstroem over 3 years ago
quantus - v0.1.5
What's Changed 🎉
- New metrics:
- Consistency and Sufficiency #112 by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/117
- Focus implementation by @FerranPares in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/127
- Fix typing issue explanation_func.py by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/120
- Issue #125 fixed, 1st attempt by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/126
- Avoid empty prints when no deprecation warnings by @vedal in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/128
- Minor fixes by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/132, including:
New Contributors
@vedal made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/128
@FerranPares made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/127
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.1.4...v0.1.5
- Jupyter Notebook
Published by annahedstroem over 3 years ago
quantus - v0.1.4
In the spotlight 🎉
- New evaluation metrics: (In)fidelity and ROAD
- Updated to a more generous LGPL license model, allowing for commercial use
- Additional functionality for faithfulness metrics e.g., computing AUC scores
- Cleaning up perturb function and supporting multi-dimensional channels
- Smaller typos and bugs fixed :-)
What's Changed
- Issue #71 and minor bug fixes by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/81
- Merging flexible input size support by @leanderweber in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/86
- Added a random uniform explanation method by @Wickstrom in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/97
- Fix typos and verify targets by @rodrigobdz in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/99
- added softmax_act param by @Wickstrom in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/102
- fixed a few typos in the readme overview section by @sltzgs in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/100
- Cleaning up Perturb Functions, Multidimensional Channel support by @leanderweber in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/88
- Update LICENSE to LGPL by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/109
- Update LICENSE to LGPL by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/108
- Included auc or mean aggregation to faithfulness metrics. by @Wickstrom in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/105
- Issues #55 #104, #106, #110 and #113: smaller bug fixes by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/114
- Infidelity (Issue 72) & Road (Issue 76) by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/107
New Contributors
- @sltzgs made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/100
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.1.3...v0.1.4
- Jupyter Notebook
Published by annahedstroem almost 4 years ago
quantus - v0.1.3
What's Changed
- WIP: 1d and non squared 2d input shapes by @dkrako in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/74
- fixing image distortion on mobile screens by @sebastian-lapuschkin in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/85
Fixed issues
Other commits
- post-merge fixes: impr. code coverage, formatting, docstrings, tytori…
- bug fixes: from self.lastresult to self.lastresults
- updated perturbfunc for inputshift
- fixes: axiomatic metrics, warnings, featuresinstep extension, defau…
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.1.2...v0.1.3
- Jupyter Notebook
Published by annahedstroem almost 4 years ago
quantus - v0.1.2
What's Changed
- updating readme to reflect arxiv submission by @sebastian-lapuschkin in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/63
- Readme: Fix minor typos by @rodrigobdz in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/64
- minor typo corrections by @dkrako in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/68
- add tqdm progress bar for faithfullness metrics by @dkrako in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/69
New Contributors
- @rodrigobdz made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/64
- @dkrako made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/68
Fixes
- @annahedstroem Fixed PixelFlipping metric only flips first color channel (https://github.com/understandable-machine-intelligence-lab/Quantus/commit/b0d6554f40556ce12ede0cb5abceba2114f83ffc)
- @annahedstroem updated a workflow guide to Contributing
- @annahedstroem added functionality to specify seed in randomisation tests
Full Changelog: https://github.com/understandable-machine-intelligence-lab/Quantus/compare/v0.1.1...v0.1.2
PyPi package here: https://pypi.org/project/quantus/0.1.2/
- Jupyter Notebook
Published by annahedstroem almost 4 years ago
quantus - v0.1.1
What's Changed
Basic interfaces and functionality by @3-nan in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/1
Modular structure by @3-nan in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/2
Experimenting by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/3
Measures utils by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/4
Measures utils by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/6
restructure, update .gitignore by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/7
Measures utils by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/10
Localization tests by @3-nan in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/5
Measures utils by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/11
Randomization and Localization Metrics by @3-nan in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/12
Measures utils by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/13
Tutorials by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/14
Tutorials by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/15
Tutorials by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/17
Tutorials by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/18
Updated docstrings by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/19
small fixes by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/20
Fixes by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/21
Fixes by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/22
Fixes by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/23
updated warnings by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/24
Reformatter black, update README.md and helper funcs by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/25
Fixes by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/26
Tests by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/27
Bug fixes localisation and faithfulness code, including some helpers … by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/29
Fixes pytests by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/30
Fixes pytests by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/31
Fixes pytests by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/32
Fixes pytests by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/33
updates: fixes, pytests and code formatting by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/34
minor fixes faithfulness and randomisation scripts by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/35
Fixes pytests by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/36
pypi package deployment updates by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/42
Fixes pytests by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/44
Update python-package.yml by @annahedstroem in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/45
Edit reshape of mask in pointing game by @Wickstrom in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/46
Adding background transparency to Quantus logo by @sebastian-lapuschkin in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/47
TF2 for Quantus by @dilyabareeva in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/50
Merge libraryagnostic with zennitand_bugfix updates into main by @dleanderweberin https://github.com/understandable-machine-intelligence-lab/Quantus/pull/59
New Contributors
- @3-nan made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/1
- @annahedstroem made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/3
- @Wickstrom made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/46
- @sebastian-lapuschkin made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/47
- @dilyabareeva made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/50
- @leanderweber made their first contribution in https://github.com/understandable-machine-intelligence-lab/Quantus/pull/59
- Jupyter Notebook
Published by annahedstroem about 4 years ago