{"id":19881728,"url":"https://github.com/ajlearner46/image-caption-generator","last_synced_at":"2025-10-17T19:05:12.454Z","repository":{"id":176218722,"uuid":"655168058","full_name":"AJlearner46/Image-Caption-Generator","owner":"AJlearner46","description":"Genrate descriptive captions for images using VGG16-LSTM","archived":false,"fork":false,"pushed_at":"2024-09-07T18:49:28.000Z","size":6523,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-01T02:47:23.591Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://image-captioin-generator-aj.streamlit.app/","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/AJlearner46.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":"2023-06-18T05:10:57.000Z","updated_at":"2024-09-07T18:49:32.000Z","dependencies_parsed_at":null,"dependency_job_id":"e64ff2ac-1c63-41d7-9934-b44c642d3ec2","html_url":"https://github.com/AJlearner46/Image-Caption-Generator","commit_stats":null,"previous_names":["ajlearner46/image-caption-generator"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AJlearner46/Image-Caption-Generator","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AJlearner46%2FImage-Caption-Generator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AJlearner46%2FImage-Caption-Generator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AJlearner46%2FImage-Caption-Generator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AJlearner46%2FImage-Caption-Generator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AJlearner46","download_url":"https://codeload.github.com/AJlearner46/Image-Caption-Generator/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AJlearner46%2FImage-Caption-Generator/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260221377,"owners_count":22976863,"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":[],"created_at":"2024-11-12T17:15:08.983Z","updated_at":"2025-10-17T19:05:12.381Z","avatar_url":"https://github.com/AJlearner46.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Image-Caption-Generator\n\nWhile humans can interpret these images without detailed captions, machines require some form of image captions for automatic understanding.\n\nThis project aims to develop an end-to-end solution for generating descriptive captions for images using deep learning techniques.\n\ndemo : https://image-captioin-generator-aj.streamlit.app/\n\n## Dataset\n- flickr dataset link :- https://www.kaggle.com/datasets/adityajn105/flickr8k\n- I used the Flickr8k Dataset, which contains 8092 photographs and text descriptions. Dataset contain 5 caption for each Image\n\n## Methodology for Image Captioning\n\n### 1. Data Preprocessing\n- Extract image features\n- Text preprocessing\n- Train-Test split\n- Data generator\n\n### 2. Encoder-Decoder Architecture\n- Load VGG16 model\n- Encoder : \n       Image feature layer\n       Sequence feature layer\n- Decoder\n  ![image](https://github.com/AJlearner46/Image-Caption-Generator/assets/99804336/803e22b8-1536-40af-bf5a-06ca78e5c405)\n\n\n### 3. Training \u0026 Optimization\n- Training model\n- Evaluation of model\n\n### 4. Frontend\n- User interface using streamlit.\n ![image](https://github.com/AJlearner46/Image-Caption-Generator/assets/99804336/5002201c-47b3-4946-90d4-8b9022590058)\n\n\n## Results\n- The VGG16-LSTM model was trained for 20 epochs, achieving a low training loss of 2.1828.\n- I evaluated the model using the BLEU score, with a focus on BLEU-1 score (0.536631).\n ![image](https://github.com/AJlearner46/Image-Caption-Generator/assets/99804336/2629f4da-0290-4d1d-a0dc-d90135f1288f)\n\n\n\n\n#### Model :- https://www.kaggle.com/code/ajr094/image-caption-generator/output?select=best_model.h5\n#### Kaggle NoteBook :- https://www.kaggle.com/code/ajr094/image-caption-generator/notebook\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fajlearner46%2Fimage-caption-generator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fajlearner46%2Fimage-caption-generator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fajlearner46%2Fimage-caption-generator/lists"}