Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/adrhill/test-data-innvestigate

https://github.com/adrhill/test-data-innvestigate

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.5%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: adrhill
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 25.4 MB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 5 years ago · Last pushed about 4 years ago
Metadata Files
Readme License

README.md

test-data-innvestigate

This repo provides test data for development of the iNNvestigate library and future LRP implementations. iNNvestigate release 1.0.9 is used to generate the data.

Installation

To ensure reproducible generation of the data, install this repo with Poetry. Make sure you have a local installation of Python 3.6 and run: bash poetry install

Usage

Generate data by running: bash poetry run test-data-innvestigate

The generated data can then be found in the created data directory and is split in two folders: * data/vgg16: sample input, layer-wise relevances and attributions for most analyzers and presets implemented in iNNvestigate on VGG16 * data/layer: attributions from randomly generated layers

All data is saved in HDF5 format. To use this data in Python, refer to the h5py docs. <!-- New LRP implementations should match the test datasets within a pixel-wise tolerance of 1e-5! -->

File structure

data/vgg16

In case the analyzer used to generate the data is of iNNvestigate's type ReverseAnalyzerBase, all intermediate Tensors are saved by their Node ID: ├── input ├── attribution └── layerwise_relevances/ └── [NODE ID] Additional attributes / metadata: * analyzer_name: name of the iNNvestigate analyzer used to generate the file * model_name: name of the model, in this case vgg16 * input_name: name of the input image used to generate the data

data/layer

For each analyzer, the dataset contains the attributions calculated for all layer types: ├── input └── [Layer name] ├── weights ├── output └── attribution Additional attributes / metadata: * analyzer_name: name of the iNNvestigate analyzer used to generate the file

Owner

  • Name: Adrian Hill
  • Login: adrhill
  • Kind: user
  • Location: Berlin
  • Company: TU Berlin

PhD student @ TU Berlin

GitHub Events

Total
Last Year

Committers

Last synced: 11 months ago

All Time
  • Total Commits: 49
  • Total Committers: 1
  • Avg Commits per committer: 49.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Adrian Hill a****l@m****g 49
Committer Domains (Top 20 + Academic)
mailbox.org: 1

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

poetry.lock pypi
  • appdirs 1.4.4 develop
  • astroid 2.9.0 develop
  • bandit 1.7.1 develop
  • black 20.8b1 develop
  • click 8.0.4 develop
  • flake8 3.9.2 develop
  • flake8-black 0.2.5 develop
  • flake8-bugbear 21.11.29 develop
  • flake8-builtins 1.5.3 develop
  • flake8-docstrings 1.6.0 develop
  • flake8-isort 4.1.1 develop
  • flake8-polyfill 1.0.2 develop
  • gitdb 4.0.9 develop
  • gitpython 3.1.20 develop
  • isort 5.8.0 develop
  • lazy-object-proxy 1.7.1 develop
  • mccabe 0.6.1 develop
  • mypy-extensions 0.4.3 develop
  • pathspec 0.9.0 develop
  • pbr 5.8.1 develop
  • pep8-naming 0.11.1 develop
  • platformdirs 2.4.0 develop
  • pycodestyle 2.7.0 develop
  • pydocstyle 6.1.1 develop
  • pyflakes 2.3.1 develop
  • pylint 2.12.0 develop
  • regex 2022.1.18 develop
  • rope 0.18.0 develop
  • smmap 5.0.0 develop
  • snowballstemmer 2.2.0 develop
  • stevedore 3.5.0 develop
  • testfixtures 6.18.4 develop
  • typed-ast 1.5.2 develop
  • wrapt 1.13.3 develop
  • absl-py 1.0.0
  • astor 0.8.1
  • atomicwrites 1.4.0
  • attrs 21.4.0
  • cached-property 1.5.2
  • colorama 0.4.4
  • dataclasses 0.8
  • future 0.18.2
  • gast 0.5.3
  • grpcio 1.44.0
  • h5py 3.1.0
  • importlib-metadata 4.8.3
  • importlib-resources 5.4.0
  • iniconfig 1.1.1
  • innvestigate 1.0.9
  • keras 2.2.4
  • keras-applications 1.0.8
  • keras-preprocessing 1.1.2
  • markdown 3.3.6
  • numpy 1.16.6
  • packaging 21.3
  • pillow 8.4.0
  • pluggy 1.0.0
  • protobuf 3.19.4
  • py 1.11.0
  • pyparsing 3.0.7
  • pytest 6.2.5
  • pyyaml 6.0
  • scipy 1.5.4
  • six 1.16.0
  • tensorboard 1.12.2
  • tensorflow 1.12.3
  • termcolor 1.1.0
  • toml 0.10.2
  • tqdm 4.63.0
  • typing-extensions 4.1.1
  • werkzeug 2.0.3
  • zipp 3.6.0
pyproject.toml pypi
  • bandit ^1.7.0 develop
  • black * develop
  • flake8 ^3.8.4 develop
  • flake8-black ^0.2.1 develop
  • flake8-bugbear ^21.3.1 develop
  • flake8-builtins ^1.5.3 develop
  • flake8-docstrings ^1.5.0 develop
  • flake8-isort ^4.0.0 develop
  • isort ^5.8.0 develop
  • pep8-naming ^0.11.1 develop
  • pylint ^2.8.2 develop
  • pytest ^6.2.2 develop
  • rope ^0.18.0 develop
  • Keras 2.2.4
  • Pillow ^8.0
  • h5py ^3.1.0
  • innvestigate 1.0.9
  • numpy 1.16.*
  • python 3.6.*
  • tensorflow 1.12.*
  • tqdm ^4.58.0