{"id":18736710,"url":"https://github.com/digitalslidearchive/albench","last_synced_at":"2025-04-12T19:31:49.361Z","repository":{"id":39846751,"uuid":"451947769","full_name":"DigitalSlideArchive/ALBench","owner":"DigitalSlideArchive","description":"Benchmarking tool for evaluating Active Learning strategies for machine learning","archived":false,"fork":false,"pushed_at":"2024-09-04T13:33:13.000Z","size":21588,"stargazers_count":5,"open_issues_count":3,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-26T14:01:40.261Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DigitalSlideArchive.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-01-25T16:09:53.000Z","updated_at":"2024-09-04T13:33:18.000Z","dependencies_parsed_at":"2024-01-11T20:23:02.421Z","dependency_job_id":"ed13648d-7ecb-4c07-8df3-5359f330c729","html_url":"https://github.com/DigitalSlideArchive/ALBench","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DigitalSlideArchive%2FALBench","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DigitalSlideArchive%2FALBench/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DigitalSlideArchive%2FALBench/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DigitalSlideArchive%2FALBench/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DigitalSlideArchive","download_url":"https://codeload.github.com/DigitalSlideArchive/ALBench/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248621132,"owners_count":21134753,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-07T15:22:12.086Z","updated_at":"2025-04-12T19:31:47.782Z","avatar_url":"https://github.com/DigitalSlideArchive.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ALBench\n(A)ctive (L)earning (Bench)marking tool:\nThis is a benchmarking tool for evaluating active learning strategies for machine\nlearning.\n\n## Overview\n\nThe tool takes an input dataset, machine learning model, and active learning strategy\nand outputs information to be used in evaluating how well the strategy does with that\nmodel and dataset.  By running the tool multiple times with different inputs, the tool\nallows comparisons across different active learning strategies and also allows\ncomparisons across different models and across different datasets.  Researchers can use\nthe tool to test proposed active learning strategies in the context of a specific model\nand dataset; or multiple models and datasets can be used to get a broader picture of\neach strategy's effectiveness in multiple contexts.  As an alternative use case,\nmultiple runs of the tool with different models and datasets can be compared, evaluating\nthese models and datasets for their compatibility with a given active learning strategy.\n\n![ALBench Overview](Documentation/ALBenchOverview.png)\nThe top-level code creates and configures handlers for the dataset, machine learning\nmodel, and active learning strategy.  Then it invokes the active learning strategy\nhandler to evaluate the strategy on the dataset using the model.\n\n## Installation\nDownload the source code using\n\n    git clone https://github.com/DigitalSlideArchive/ALBench.git\n\nor a similar command.  Then install it with `pip` using the name of the directory that you downloaded to:\n\n    pip install ./ALBench\n\nIf you wish to use the `al_bench.model` or `al_bench.strategy` subpackage you will also need to install `tensorflow` and `torch`.  If you wish to use `batchbald_redux` you will need that too:\n\n    pip install 'tensorflow\u003c3.0' 'torch\u003c2.0' batchbald_redux\n\n(Torch can be hard to install.  See its installation instructions for help.)\n\n## Using `al_bench`\nImport the top-level package and each subpackage you wish to use\n\n    import al_bench as alb\n    import al_bench.dataset, al_bench.model, al_bench.strategy, al_bench.factory\n    # Use alb.dataset.*, alb.model.*, etc.\n\nSee [SimpleExample.ipynb](example/SimpleExample.ipynb) for a simple example of the `dataset`, `model`, and `strategy` subpackages.  See [test/test_0040_factory.py](test/test_0040_factory.py) for an example use of the `factory` subpackage.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdigitalslidearchive%2Falbench","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdigitalslidearchive%2Falbench","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdigitalslidearchive%2Falbench/lists"}