AIX360 | Interpretability and explainability of data and machine learning models | Machine Learning library

by Trusted-AI Python Version: 0.3.0 License: Apache-2.0

X-Ray Key Features Code Snippets(1)Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | AIX360 Summary

AIX360 is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Pytorch applications. AIX360 has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has medium support. You can install using 'pip install AIX360' or download it from GitHub, PyPI.

The AI Explainability 360 toolkit is an open-source library that supports interpretability and explainability of datasets and machine learning models. The AI Explainability 360 Python package includes a comprehensive set of algorithms that cover different dimensions of explanations along with proxy explainability metrics. The AI Explainability 360 interactive experience provides a gentle introduction to the concepts and capabilities by walking through an example use case for different consumer personas. The tutorials and example notebooks offer a deeper, data scientist-oriented introduction. The complete API is also available. There is no single approach to explainability that works best. There are many ways to explain: data vs. model, directly interpretable vs. post hoc explanation, local vs. global, etc. It may therefore be confusing to figure out which algorithms are most appropriate for a given use case. To help, we have created some guidance material and a chart that can be consulted.

Support

Quality

Security

License

Reuse

Support

AIX360 has a medium active ecosystem.

It has 1320 star(s) with 284 fork(s). There are 52 watchers for this library.

There were 1 major release(s) in the last 12 months.

There are 43 open issues and 29 have been closed. On average issues are closed in 32 days. There are 11 open pull requests and 0 closed requests.

It has a neutral sentiment in the developer community.

The latest version of AIX360 is 0.3.0

Quality

AIX360 has 0 bugs and 0 code smells.

Security

AIX360 has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

AIX360 code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

AIX360 is licensed under the Apache-2.0 License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

AIX360 releases are available to install and integrate.

Deployable package is available in PyPI.

Build file is available. You can build the component from source.

Installation instructions, examples and code snippets are available.

AIX360 saves you 2083 person hours of effort in developing the same functionality from scratch.

It has 5177 lines of code, 283 functions and 93 files.

It has medium code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed AIX360 and discovered the below as its top functions. This is intended to give you an instant insight into AIX360 implemented functionality, and help decide if they suit your requirements.

Compute the feature indicator matrix
Perform beam search
Compute the lambda function
Evaluate singular values
Probe the probe model for the training
A fully connected layer
Learn the rule
Beam search
Resnet model
Resnet layer
Fit the model
Plots the latent traversal transformation
Generate matplotlib plot
An explanation of the DnF rule
Add label and explanation to dataset
Generate random features
Calculates the accuracy of a simple model
Plots the latent traversal traversal
Predict for the given data
Forward the layer
Plot the reconstruction of the trained network
Downloads the cifar - 10 dataset
Return an example for the given example id
Predict for each feature
FeatureBinarizer
Uses FFT
Computes confusion matrix
Return the explanation of X

Get all kandi verified functions for this library.

AIX360 Key Features

No Key Features are available at this moment for AIX360.

AIX360 Examples and Code Snippets

Keras, AIX360(LIME) - ValueError: the input array must be have a shape == (.., ..,[ ..,] 3)), got (28, 28, 1)

Python

Lines of Code : 14

License : Strong Copyleft (CC BY-SA 4.0)

Copy

def to_rgb(x):
    x_rgb = np.zeros((x.shape[0], 28, 28, 3))
    for i in range(3):
        x_rgb[..., i] = x[..., 0]
    return x_rgb

train_rgb = to_rgb(train)
test_rgb = to_rgb(test)

limeExplainer.explain_instan

Community Discussions

Trending Discussions on AIX360

Keras, AIX360(LIME) - ValueError: the input array must be have a shape == (.., ..,[ ..,] 3)), got (28, 28, 1)

QUESTION

Keras, AIX360(LIME) - ValueError: the input array must be have a shape == (.., ..,[ ..,] 3)), got (28, 28, 1)

Asked 2020-Aug-03 at 21:11

I am trying to make some program using a model from Keras and then explain it with Lime explainer from AIX360 (which is just wrapper for the original LIME). All the data are MNIST grayscale digits. But in my case, I am not able to explain the instance because I can't figure out what to feed to the explainers.

My code:

...

ANSWER

Answered 2020-Aug-03 at 19:26

I added this conversion and trained on RGB images:

Source https://stackoverflow.com/questions/63231969

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install AIX360

Clone the latest version of this repository:. If you'd like to run the examples and tutorial notebooks, download the datasets now and place them in their respective folders as described in aix360/data/README.md.
If you would like to quickly start using the AI explainability 360 toolkit without cloning this repository, then you can install the aix360 pypi package as follows. If you follow this approach, you may need to download the notebooks in the examples folder separately.