{"id":20100346,"url":"https://github.com/bbenligiray/rml-cnn","last_synced_at":"2025-06-27T05:32:56.386Z","repository":{"id":130691756,"uuid":"147312700","full_name":"bbenligiray/rml-cnn","owner":"bbenligiray","description":"Semi-Supervised Robust Deep Neural Networks for Multi-Label Classification","archived":false,"fork":false,"pushed_at":"2019-12-30T12:24:56.000Z","size":137,"stargazers_count":17,"open_issues_count":1,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-05-06T06:46:46.966Z","etag":null,"topics":["loss-functions","multi-label-classification","robust-machine-learning","semi-supervised-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bbenligiray.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null}},"created_at":"2018-09-04T08:23:58.000Z","updated_at":"2023-08-01T02:04:40.000Z","dependencies_parsed_at":null,"dependency_job_id":"3eb99326-8754-4a2b-8ae7-f2e25a709f27","html_url":"https://github.com/bbenligiray/rml-cnn","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bbenligiray/rml-cnn","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bbenligiray%2Frml-cnn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bbenligiray%2Frml-cnn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bbenligiray%2Frml-cnn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bbenligiray%2Frml-cnn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bbenligiray","download_url":"https://codeload.github.com/bbenligiray/rml-cnn/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bbenligiray%2Frml-cnn/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259399437,"owners_count":22851628,"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":["loss-functions","multi-label-classification","robust-machine-learning","semi-supervised-learning"],"created_at":"2024-11-13T17:15:15.905Z","updated_at":"2025-06-27T05:32:56.379Z","avatar_url":"https://github.com/bbenligiray.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RML-CNN\n\nCode covering some of the experiments in the following paper:\n\n[Cevikalp, H., Benligiray, B., Gerek, O. N.. (2019). Semi-Supervised Robust Deep Neural Networks for Multi-Label Image Classification. In Pattern Recognition.](https://www.sciencedirect.com/science/article/abs/pii/S0031320319304649)\n\nUse [this](https://github.com/bbenligiray/nus_wide_formatter_SRN) to create a `nus_wide.h5` and [this](https://github.com/bbenligiray/ms_coco_formatter_SRN) to create a `ms_coco.h5` file. Download `resnet101_weights_tf.h5` from [here](https://gist.github.com/flyyufelix/65018873f8cb2bbe95f429c474aa1294). Put these in `/rml-cnn`, then run `run.sh` to run the experiments.\n\nAlternatively, you can use the loss functions in `ml_loss` with any model/dataset you like, see `main.py` for reference. Note that your final layer's activation should be `None` for all loss functions (including softmax).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbbenligiray%2Frml-cnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbbenligiray%2Frml-cnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbbenligiray%2Frml-cnn/lists"}