{"id":15567238,"url":"https://github.com/iml1111/pytorch-recommender","last_synced_at":"2025-03-29T05:35:04.092Z","repository":{"id":103823046,"uuid":"377755616","full_name":"iml1111/Pytorch-Recommender","owner":"iml1111","description":"Neural Recommendation System Using PyTorch","archived":false,"fork":false,"pushed_at":"2022-10-07T05:56:27.000Z","size":98223,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-03T15:55:47.794Z","etag":null,"topics":["deep-learning","pytorch","recommender-system","tutorial"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/iml1111.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":"2021-06-17T08:16:31.000Z","updated_at":"2023-03-07T07:15:59.000Z","dependencies_parsed_at":"2023-07-13T10:46:08.642Z","dependency_job_id":null,"html_url":"https://github.com/iml1111/Pytorch-Recommender","commit_stats":{"total_commits":23,"total_committers":2,"mean_commits":11.5,"dds":0.4347826086956522,"last_synced_commit":"743e2b55828494731ff3c15101847df524ba3028"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iml1111%2FPytorch-Recommender","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iml1111%2FPytorch-Recommender/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iml1111%2FPytorch-Recommender/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iml1111%2FPytorch-Recommender/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iml1111","download_url":"https://codeload.github.com/iml1111/Pytorch-Recommender/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246145014,"owners_count":20730494,"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":["deep-learning","pytorch","recommender-system","tutorial"],"created_at":"2024-10-02T17:10:27.351Z","updated_at":"2025-03-29T05:35:04.074Z","avatar_url":"https://github.com/iml1111.png","language":"Python","readme":"# Pytorch-Recommender\n**Neural Recommendation System Using PyTorch**\n\n본 repo는 추천시스템을 공부하며, 대표적인 알고리즘들을 Pytorch를 사용하여 직접 구현해본 실습 예제 코드입니다. 해당 코드 및 데이터셋은논문에 나온 코드의 동작 구조 재현 자체에 초점을 맞추었으며,  별도의 전처리 및 튜닝을 거치지 않았기 때문에 좋은 성능을 기대하기는 어렵습니다.\n\n**실제 코드의 흐름만 파악해주셨으면 합니다!** \n\n## Algorithms\n\n- [Neural-Collaborative-Filtering](https://arxiv.org/pdf/1708.05031.pdf)\n- [Wide-Deep-Learning](https://arxiv.org/pdf/1606.07792.pdf)\n- [DeepFM](https://arxiv.org/abs/1703.04247)\n- [AutoEncoder-Meet-Collaborative-Filtering](https://users.cecs.anu.edu.au/~akmenon/papers/autorec/autorec-paper.pdf)\n\n\n\n## Get Started\n\n각 파트에 맞는 디렉터리에 들어가셔서 일관적으로 train.py를 실행하시면 됩니다. 기본적으로 모든 default param이 설정되어 있고, 아래와 같이 --help option을 사용하여 연결된 input param을 확인하실 수 있습니다.\n\n```shell\n$ python train.py -h\nusage: train.py [-h] [--model_fn MODEL_FN] [--data_path DATA_PATH]\n                [--batch_size BATCH_SIZE] [--n_epochs N_EPOCHS]\n                [--embed_dim EMBED_DIM] [--mlp_dims MLP_DIMS]\n                [--train_ratio TRAIN_RATIO] [--valid_ratio VALID_RATIO]\n\noptional arguments:\n  -h, --help            show this help message and exit\n  --model_fn MODEL_FN   Model file name to save. Additional information would\n                        be annotated to the file name.\n  --data_path DATA_PATH\n                        Dataset Path,\n                        Default=../data/kmrd/kmr_dataset/datafile/kmrd-\n                        small/rates.csv\n  --batch_size BATCH_SIZE\n                        Mini batch size for gradient descent. Default=256\n  --n_epochs N_EPOCHS   Number of epochs to train. Default=30\n  --embed_dim EMBED_DIM\n                        Embedding Vector Size. Default=100\n  --mlp_dims MLP_DIMS   MultiLayerPerceptron Layers size. Default=[16, 16, 16]\n  --train_ratio TRAIN_RATIO\n                        Train data ratio. Default=0.8\n  --valid_ratio VALID_RATIO\n                        Valid data ratio. Default=0.1\n```\n\n\n\n## Dataset\n\n다음과 같은 방식으로 각각의 데이터셋을 다운로드할 수 있습니다. \u003cbr\u003e\n데이터셋의 설치 경로는 자유이지만, 실행전에 각 실행 코드의 DATA_PATH를 확인해주세요.\n\n### KMRD\n```shell\n$ mkdir src/data \u0026\u0026 cd data/\n$ git clone https://github.com/lovit/kmrd \u0026\u0026 cd kmrd/\n$ python setup.py install\n# ~\\Pytorch-Recommender\\src\\data\\kmrd\\kmr_dataset\\datafile\\kmrd-small\n```\n\n## References\n\n- [torchfm](https://pypi.org/project/torchfm/)\n- [DeepCTR-Torch](https://github.com/shenweichen/DeepCTR-Torch)\n- [DeepRecommender](https://github.com/NVIDIA/DeepRecommender)\n- [FactorizationMachine](https://www.csie.ntu.edu.tw/~b97053/paper/Rendle2010FM.pdf)\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiml1111%2Fpytorch-recommender","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fiml1111%2Fpytorch-recommender","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiml1111%2Fpytorch-recommender/lists"}