tf-al 0.0.2

Active learning with tensorflow. Create custom and generic active learning loops. Export and share your experiments.

Active learning with tensorflow

Index

1. Installation
2. Getting started
   1. Model wrapper
   2. Acquisition functions
   3. Basic active learning loop
3. Development
   1. Setup
   2. Scripts
4. Contribution
5. Issues

Installation

$ pip install tf-al

Getting started

The library

Model wrapper

Model wrappers are use to create interfaces to the active learning loop.

Acquisition functions

Basic active learning loop

import tensorflow as tf
from tf_al import ActiveLearningLoop, Dataset, Pool

Development

Setup

1. Create a virtual env (optional)
2. Install and Setup Poetry
3. Install package dependencies using poetry

Scripts

Create documentation

To create documentation for the ./active_leanring directory. Execute following command in ./docs

$ make html

Run tests

To perform automated unittests run following command in the root package directory.

$ pytest

To generate additional coverage reports run.

$ pytest --cov

Contribution

Issues