{"id":18295447,"url":"https://github.com/quanpersie2001/imagecaptioning","last_synced_at":"2025-10-28T20:15:13.429Z","repository":{"id":160783036,"uuid":"577608057","full_name":"quanpersie2001/ImageCaptioning","owner":"quanpersie2001","description":"Predicting a caption for a given image using Inception Net V3, LSTM and Glove","archived":false,"fork":false,"pushed_at":"2023-05-20T19:35:34.000Z","size":15071,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-15T02:43:20.570Z","etag":null,"topics":["cnn","image-captioning","imagecaptioning","inception-v3","lstm","rnn"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/quanpersie2001.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":"2022-12-13T05:40:41.000Z","updated_at":"2024-09-10T15:01:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"99b583c6-96cf-48d3-83c0-271402a93ffd","html_url":"https://github.com/quanpersie2001/ImageCaptioning","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/quanpersie2001%2FImageCaptioning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/quanpersie2001%2FImageCaptioning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/quanpersie2001%2FImageCaptioning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/quanpersie2001%2FImageCaptioning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/quanpersie2001","download_url":"https://codeload.github.com/quanpersie2001/ImageCaptioning/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248002598,"owners_count":21031632,"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","image-captioning","imagecaptioning","inception-v3","lstm","rnn"],"created_at":"2024-11-05T14:35:30.291Z","updated_at":"2025-10-28T20:15:08.388Z","avatar_url":"https://github.com/quanpersie2001.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Image Captioning\n## Model using Inception Net V3, LSTM and Glove (Using SSD300 to improve feature)\n\n![image](model.png)\n\n## How to run?\n### Install lib\n```\npip install -r requirements.txt\n```\n\n### Download data\n```console\npython data_download.py\n```\n\u003e **Note** : Dataset is MS COCO 2014 and Glove \u003cWikipedia 2014 + Gigaword 5\u003e. This is large dataset, long download.\n### Preprocess\nYou **must** run\n```console\npython preprocess.py\n```\nWith COCO datase this command runs for a long time you can download and coppy them to `ROOT / process_data`\n\n### [Download here](https://drive.google.com/drive/folders/1HDgToaiFKzVNTQZI1ts2Dlfgh1sVMk3D?usp=sharing)\n\n### Trainning\n```console\npython train.py --batch-size 64 --output weights --epochs 30\n```\nYou can download pre-train model an copy them to `ROOT / weights`\n### [Download here](https://drive.google.com/drive/folders/1oXVC8fVioblaRpvB-tVtQsBHwKTmfMse?usp=sharing)\n\n### Predict\n```console\npython predict.py --image path/to/image --weight path/to/weight --k-beam 9\n```\n\n## Result\n![image](output.png)\nYou can see sumary in [summary.ipynb](summary.ipynb)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fquanpersie2001%2Fimagecaptioning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fquanpersie2001%2Fimagecaptioning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fquanpersie2001%2Fimagecaptioning/lists"}