alibi
alibi copied to clipboard
SeldonIO
Algorithms for explaining machine learning models
After 0.7.0 we should add a section in this page (and the corresponding notebook) to discuss similarity explanations.
What are the different quantitative evaluation metrics that can be used to evaluate the performance / accuracy etc of the anchors algorithm? I am looking to use this for an...
I have a CNN that performs a classification operation (classifying an image into 1 of two classes - "Fake" or "Real") and I want to obtain the anchors for a...
Incoprorate [this](https://hanxiao.io/2019/11/07/A-Better-Practice-for-Managing-extras-require-Dependencies-in-Python/) pattern into `extras_require` in `setup.py` as will be cleaner to maintain. Note: The reason this was not done in #583 was due to `dependabot` not tracking the `extra_requirements.txt`...
Add [nbstripout](https://github.com/kynan/nbstripout) as a pre-commit-hook. `nbstripout` is configured to remove everything except the cell outputs. I've also run it against all the files.
Hi all, I'm trying to use Anchor Tabular on a new model, but I cannot fit the anchor. The model works with missing data so initially I've been using missing...
Consider adding explicit type hints in TabularSampler for `feature_names: list, feature_values: dict` and others. https://github.com/SeldonIO/alibi/blob/73eabdacbdb08a75494955a9affbb800ac73abbb/alibi/explainers/anchor_tabular.py#L17-L24
The `AnchorText` with `LangugeModel` does not work with [tokenizers v0.12.0](https://github.com/huggingface/tokenizers/releases/tag/v0.12.0). The issue comes from the `tokenizer.convert_tokens_to_string` which no longer returns a `str` as it signature suggests, but a `List[str]`. To...
Hi there, I'm trying to get explanation for a classification model (TFCamembertForSequenceClassification fine-tuned on some data) using the IntegratedGradients explainer. I'm following this great [tutorial ](https://docs.seldon.io/projects/alibi/en/latest/examples/integrated_gradients_transformers.html) and I have an...
Just shifted from that original Anchor implementation (implemented by paper's author), encounted a problem so wonder if it is exist in this implementation too. My features had been encoded into...
