lime icon indicating copy to clipboard operation
lime copied to clipboard

Lime: Explaining the predictions of any machine learning classifier

Results 121 lime issues
Sort by recently updated
recently updated
newest added

Environment: lime -- 0.2.0.1 I just followed the document and just changed the image path. --- ``` def get_pil_transform(): transf = transforms.Compose([ transforms.Resize((224, 224)), # transforms.CenterCrop(224) ]) return transf def...

Not sure if this is the accurate way as I also searched for it a lot and didn't find any answer. But I'm doing it this way: - Save the...

Due to [pyDOE2](https://pypi.org/project/pyDOE2/) being a dependent in setup.py, Python is supported up to 3.6. By upgrading to [pyDOE**3**](https://pypi.org/project/pyDOE3/), Python's constraint can be lifted to 3.11.

Hi Community! I’ve noticed a potential issue with using the LIME package for ML model explainability, and I’d appreciate some clarification. Given that LIME is a local method, it generates...

Good evening, is it possible to use LIME for text generation tasks? Or only for classification? Thanks

![image](https://github.com/marcotcr/lime/assets/21102805/c86844ea-a22a-4a04-b713-8a0bbd2c6438) I have only one column wind direction but in plot it is coming as Wind direction_t-1, wind_direction_t-2. I am using RecurrentTabularExplainer for regression task.

As per my comment in #443 I added the option to specify a background color. Works for both saving the HTML (required some reformatting of the HTML) and in notebook....

Is this a possibility? Because as_pyplot_figure just saves a bar graph and the output shown in the notebook seems to be much more intuitive.

The "temp" image needs to be converted to grayscale for the new version of Keras models. However, the image must be in RGB format for segmentation. Therefore, this line of...

# Add Video Explanation Support to LIME ## Overview This PR introduces video explanation capabilities to LIME through a new `LimeVideoExplainer` class, enabling the interpretation of video classification models. This...