{"id":17950126,"url":"https://github.com/jjonescz/ibb-assignment3","last_synced_at":"2025-06-21T07:04:08.367Z","repository":{"id":132787807,"uuid":"329389172","full_name":"jjonescz/ibb-assignment3","owner":"jjonescz","description":"Ear recognition using CNN based on EfficientNet-B0 (Assignment 3 for Image Based Biometry course at University of Ljubljana)","archived":false,"fork":false,"pushed_at":"2021-01-15T21:24:48.000Z","size":30853,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-08T16:42:42.527Z","etag":null,"topics":["cnn","ear-recognition","efficientnet","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"TeX","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/jjonescz.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}},"created_at":"2021-01-13T17:54:55.000Z","updated_at":"2021-01-15T21:25:27.000Z","dependencies_parsed_at":"2023-07-17T06:15:09.422Z","dependency_job_id":null,"html_url":"https://github.com/jjonescz/ibb-assignment3","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/jjonescz/ibb-assignment3","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjonescz%2Fibb-assignment3","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjonescz%2Fibb-assignment3/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjonescz%2Fibb-assignment3/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjonescz%2Fibb-assignment3/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jjonescz","download_url":"https://codeload.github.com/jjonescz/ibb-assignment3/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjonescz%2Fibb-assignment3/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261080476,"owners_count":23106595,"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":["cnn","ear-recognition","efficientnet","tensorflow"],"created_at":"2024-10-29T09:37:39.599Z","updated_at":"2025-06-21T07:04:03.357Z","avatar_url":"https://github.com/jjonescz.png","language":"TeX","funding_links":[],"categories":[],"sub_categories":[],"readme":"# IBB Assignment 3\n\nThis repository contains source code of my solution of Assignment 3 for Image\nBased Biometry course at University of Ljubljana.\n\nReport with IMRAD structure is available as [release asset](https://github.com/jjonescz/ibb-assignment3/releases).\n\n## Requirements\n\nPython 3.8.2 was used with the following packages installed:\n\n```txt\nmatplotlib==3.3.2\nnumpy==1.18.5\npandas==1.1.3\ntensorflow==2.3.1\n```\n\nAdditionally, folder `data` must contain [AWE dataset](http://awe.fri.uni-lj.si/downloads/AWEDataset.zip) unzipped so that e.g. `data/001/01.png` is a valid path.\n\n## Loading and training\n\nScript `train.py` can be run as-is.\nIt will download EfficientNet-B0 weights and load saved weights of our CNN model trained without image augmentations.\nTo switch to model with image augmentations, change parameters near top of the file to contain:\n\n```py\nEXP_ID = \"model-b\"\nAUGMENTATIONS = True\n```\n\nTo enable model training, change parameters to:\n\n```py\nTRAIN = True\n```\n\n## Evaluation\n\nScript `evaluate.py` plots figures (to folder `figures`) and prints performance metrics to console.\nIt uses state of models provided in folder `out`.\nThis state can be recomputed by executing script `train.py` (once with augmentations and once without them) as described in previous section.\n\n## Report\n\nSource code of LaTeX report is contained in `report/jj1712.tex`.\nBefore compiling it, make sure you have generated figures as described in [Evaluation](#evaluation).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjjonescz%2Fibb-assignment3","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjjonescz%2Fibb-assignment3","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjjonescz%2Fibb-assignment3/lists"}