OmniXAI v1.3.2

Update the IPython version

OmniXAI v1.3.1

Fix an issues related to the default parameters in TabularTransform.

OmniXAI v1.3.0

1. OmniXAI v1.3.0 includes an experimental GPT explainer. This explainer leverages the outcomes produced by SHAP and MACE to formulate the input prompt for ChatGPT. Subsequently, ChatGPT analyzes these results and generates the corresponding explanations that provide developers with a clearer understanding of the rationale behind the model's predictions.
2. Fixed some small issues in the explainers and visualization.
3. Updated the copyright.

OmniXAI v1.2.5

1. Add what-if analysis for tabular data, e.g., users can change feature values and compare different models.
2. Revise the visualization dashboard to support Google Colab notebooks.
3. MACE now can generate counterfactual examples without using KNN search. This feature is mainly used for small datasets.

OmniXAI v1.2.4

1. Support model bias analysis
2. Revise the documentations
3. Fix some bugs in OmniXAI v1.2.3

OmniXAI v1.2.3

1. Add global SHAP feature importance.
2. Add permutation feature importance.
3. Add a KNN-based counterfactual explainer.
4. Revise the dashboard figures for global explanations.
5. Fix some bugs and interface issues.

OmniXAI v1.2.2

1. Support BentoML deployment for TabularExplainer, VisionExplainer and NLPExplainer.
2. Support JSON converters for all the explanation classes.
3. Fix a small bug in feature visualization when Torch > 1.7.

OmniXAI v1.2.1

1. Add FFT preconditioning for feature visualization
2. Implement ScoreCAM, LayerCAM, SmoothGrad and Guided Backpropagation
3. Fix some small bugs.

OmniXAI v1.2.0

1. Support feature visualization (an optimization-based method) for vision models.
2. Allow visualizing feature maps in CNN models.
3. Add more tutorials on the supported explainers.
4. Fix some bugs in the ranking explainers.

OmniXAI v1.1.4

1. Fix a bug in the MACE refinement module.
2. Add several explainers for ranking tasks, e.g., ValidityRankingExplainer, PermutationRankingExplainer, MACEExplainer.
3. Add save and load functions for the supported explainers.
4. Add a RL-based approach for the MACE counterfactual explainer, e.g., set method = "rl" when creating a MACE explainer.