{"id":19635965,"url":"https://github.com/talkuhulk/music-genres-classification","last_synced_at":"2026-05-16T11:05:54.880Z","repository":{"id":39737061,"uuid":"193323456","full_name":"TalkUHulk/music-genres-classification","owner":"TalkUHulk","description":"Tensorflow implementation of music-genres-classification with InceptionResnetV2","archived":false,"fork":false,"pushed_at":"2023-03-24T22:59:11.000Z","size":798,"stargazers_count":2,"open_issues_count":2,"forks_count":1,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-10-28T05:34:02.836Z","etag":null,"topics":["audio-classification","classification","cnn-tensorflow","genres-classification","inception-resnet-v2","librosa","python","tensorflow"],"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/TalkUHulk.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":"2019-06-23T08:21:50.000Z","updated_at":"2022-05-11T07:03:15.000Z","dependencies_parsed_at":"2025-01-09T16:54:07.285Z","dependency_job_id":"03054a88-9964-441c-aafb-3bb8d7592d24","html_url":"https://github.com/TalkUHulk/music-genres-classification","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/TalkUHulk/music-genres-classification","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TalkUHulk%2Fmusic-genres-classification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TalkUHulk%2Fmusic-genres-classification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TalkUHulk%2Fmusic-genres-classification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TalkUHulk%2Fmusic-genres-classification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TalkUHulk","download_url":"https://codeload.github.com/TalkUHulk/music-genres-classification/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TalkUHulk%2Fmusic-genres-classification/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33100321,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-16T04:41:52.686Z","status":"ssl_error","status_checked_at":"2026-05-16T04:41:52.009Z","response_time":115,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["audio-classification","classification","cnn-tensorflow","genres-classification","inception-resnet-v2","librosa","python","tensorflow"],"created_at":"2024-11-11T12:27:49.190Z","updated_at":"2026-05-16T11:05:54.860Z","avatar_url":"https://github.com/TalkUHulk.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"![Python 3.7](https://img.shields.io/badge/python-3.7-green.svg)\n\n# music-genres-classification\n## Abstract\nThe demo is to develop a deep learning model that will identify the genres from music.The model adopt Inception-ResnetV2 from slim.And the datasat used GTZAN Music Genre Dataset, which is a collection of 1000 songs in 10 genres, is the most widely used dataset.If you wanna train a model by yourself, download it from [GTZAN dataset](http://opihi.cs.uvic.ca/sound/genres.tar.gz).\n\nBelow table shows the result on test set:\n\nAccuracy | Value\n--------- | ---------\nTop-1 | 69.70%\nTop-3 | 92.50%\n\nBelow picture shows the training-process on tensorboard:\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"tensorboard/loss.jpg\" width=\"400\"\u003e \u003cbr /\u003e\n  \u003cem\u003e Loss \u003c/em\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"tensorboard/accuracy.jpg\" width=\"400\"\u003e \u003cbr /\u003e\n  \u003cem\u003e Accuracy\u003c/em\u003e\n\u003c/p\u003e\n\n## Pre-Trained Testing\n\n* Step1: download [pre_trained](https://pan.baidu.com/s/1Pg7UH5rj_xCv77Wz4sCy_A) model,and put it into `models/` folder.\n* Step2: test by executing the following command:\n```python \npython test.py\n```\n\n## Training\n\n* Step1: download Dataset GTZAN,and put it into `GTZAN/` folder.\n* Step2: create the tfrecords by executing the following command:\n```Bash \nusage: create_data_to_train.py [-h] [--data_path DATA_PATH]\n                               [--train_path TRAIN_PATH]\n                               [--test_path TEST_PATH] [--test_size TEST_SIZE]\n                               [--aug AUG]\n```\n```Bash\noptional arguments:\n  -h, --help            show this help message and exit\n  --data_path DATA_PATH\n                        data_sets path.\n  --train_path TRAIN_PATH\n                        train tfrecords save path.\n  --test_path TEST_PATH\n                        test tfrecords save path.\n  --test_size TEST_SIZE\n                        Proportion of test data that between [0, 1]\n  --aug AUG             the size of data sets up to (arg) times as original. 1\n                        means not augmentation.                        \n\n```\n* Step3: train the model by executing the following command:\n```Bash \nusage: train.py [-h] [--train_data TRAIN_DATA] [--decay_rate DECAY_RATE]\n                [--global_steps GLOBAL_STEPS] [--decay_steps DECAY_STEPS]\n                [--learning_rate LEARNING_RATE] [--eval_step EVAL_STEP]\n                [--batch_size BATCH_SIZE] [--model_path MODEL_PATH]\n                [--summary_path SUMMARY_PATH] [--load_model LOAD_MODEL]\n```\n\n```Bash           \noptional arguments:\n  -h, --help            show this help message and exit\n  --train_data TRAIN_DATA\n                        train_data path.\n  --decay_rate DECAY_RATE\n                        learning rate decay rate.\n  --global_steps GLOBAL_STEPS\n                        global steps\n  --decay_steps DECAY_STEPS\n                        learning rate decay steps.\n  --learning_rate LEARNING_RATE\n                        learning rate.\n  --eval_step EVAL_STEP\n                        evaluation steps.\n  --batch_size BATCH_SIZE\n                        batch size.\n  --model_path MODEL_PATH\n                        tensorflow model path.\n  --summary_path SUMMARY_PATH\n                        tensorflow summary path.\n  --load_model LOAD_MODEL\n                        whether you wish to continue training.\n```\n\n## Testing\n\nRun the following command to simple test the test-dataset:\n```python \npython test.py\n```\n\n## References\n\n[1] https://github.com/deepsound-project/genre-recognition\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftalkuhulk%2Fmusic-genres-classification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftalkuhulk%2Fmusic-genres-classification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftalkuhulk%2Fmusic-genres-classification/lists"}