Interpreing image segmentation models
Project description
Interpret Segmentation
A one-stop shop for the interpretability of image segmentation models. This code was extracted from my bachelors thesis: https://github.com/andef4/thesis-code
Available algorithms:
- Hausdorff Distance Masks
- RISE
Documentation
The documentation is available on Read the Docs: https://interpret-segmentation.readthedocs.io/en/latest/.
Development
To hack on interpret-segmentation, do the following:
- Clone the git repository
- Create a new virtualenv and activate it, e.g.
python3 -m venv venv/; source venv/bin/activate
- Inside the git repository, install the library in development mode including development dependencies:
pip install -e .[dev]
- Install the flake8 pre-commit hook with
pre-commit
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 interpret_segmentation-0.0.3.tar.gz
.
File metadata
- Download URL: interpret_segmentation-0.0.3.tar.gz
- Upload date:
- Size: 5.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.1 CPython/3.6.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | f10afecf01850c6d82c778273a6115f1d00ceb86ea9b753c417ba2cfa4025ee6 |
|
MD5 | e9041c9a1ec8f3f1c3686bd29784d4ba |
|
BLAKE2b-256 | e709519694ce8fc760dce41c7582cdae033831cb92e6c092cba3219be21dc12e |
File details
Details for the file interpret_segmentation-0.0.3-py3-none-any.whl
.
File metadata
- Download URL: interpret_segmentation-0.0.3-py3-none-any.whl
- Upload date:
- Size: 7.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.1 CPython/3.6.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 61915fa71d71ae07e5bcbccd6048276cad744de4c37eb69a0dc87dca8d9971bb |
|
MD5 | 9aaf069e4e4ff097ff61aae56fccc19a |
|
BLAKE2b-256 | 0db059cf5988b8b17f6ff3bf74100d65d0767e74c68eb5e342e46eb2621cfee2 |