XAI method to explain distances in embedded spaces
Project description
distance_explainer
XAI method to explain distances in embedded spaces.
Installation
To install distance_explainer from GitHub repository, do:
git clone git@github.com:dianna-ai/distance_explainer.git
cd distance_explainer
python3 -m pip install .
How to use
See our tutorial how to use this package. In short:
image1 = np.random.random((100, 100, 3))
image2 = np.random.random((100, 100, 3))
image2_embedded = model(image2)
explainer = DistanceExplainer(axis_labels={2: 'channels'})
attribution_map = explainer.explain_image_distance(model, image1, image2_embedded)
Contributing
If you want to contribute to the development of distance_explainer, have a look at the contribution guidelines.
Credits
This package was created with Cookiecutter and the NLeSC/python-template.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file distance_explainer-0.4.0.tar.gz
.
File metadata
- Download URL: distance_explainer-0.4.0.tar.gz
- Upload date:
- Size: 11.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 10a0a76c8498556b4b68bd32e6347a5dba84cf5fc075f488eb86d123b6070bd1 |
|
MD5 | d89492e3f36aa8627eeee2222c515a39 |
|
BLAKE2b-256 | 55394447603bbf70be426360a2de405d1d7ada3f3bf8753d10c44ea87edc184f |
Provenance
The following attestation bundles were made for distance_explainer-0.4.0.tar.gz
:
Publisher:
release.yml
on dianna-ai/distance_explainer
-
Statement type:
https://in-toto.io/Statement/v1
- Predicate type:
https://docs.pypi.org/attestations/publish/v1
- Subject name:
distance_explainer-0.4.0.tar.gz
- Subject digest:
10a0a76c8498556b4b68bd32e6347a5dba84cf5fc075f488eb86d123b6070bd1
- Sigstore transparency entry: 146737094
- Sigstore integration time:
- Predicate type:
File details
Details for the file distance_explainer-0.4.0-py3-none-any.whl
.
File metadata
- Download URL: distance_explainer-0.4.0-py3-none-any.whl
- Upload date:
- Size: 9.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5925a51994d9c137380fcab658b8de4fce139480f9c3f43793b1be68453f09f5 |
|
MD5 | 6126bd2429f89546588d904330a14849 |
|
BLAKE2b-256 | 16945ed8a7c8f99c62fb54e52160bc45687ea859400dc33be8efe7c559a6d7db |
Provenance
The following attestation bundles were made for distance_explainer-0.4.0-py3-none-any.whl
:
Publisher:
release.yml
on dianna-ai/distance_explainer
-
Statement type:
https://in-toto.io/Statement/v1
- Predicate type:
https://docs.pypi.org/attestations/publish/v1
- Subject name:
distance_explainer-0.4.0-py3-none-any.whl
- Subject digest:
5925a51994d9c137380fcab658b8de4fce139480f9c3f43793b1be68453f09f5
- Sigstore transparency entry: 146737095
- Sigstore integration time:
- Predicate type: