{"id":15414307,"url":"https://github.com/naufalahnaf17/pytorch-cv-project","last_synced_at":"2026-01-11T01:35:12.988Z","repository":{"id":257371113,"uuid":"856207505","full_name":"naufalahnaf17/pytorch-cv-project","owner":"naufalahnaf17","description":"several computer vision projects in learning to create deep learning models, especially in the field of computer vision, starting from classification, object detection and others","archived":false,"fork":false,"pushed_at":"2024-09-25T17:38:13.000Z","size":2007,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-10-06T02:06:00.674Z","etag":null,"topics":["beginner-project","computer-vision","fine-tuning","huggingface","onnxruntime","python","pytorch"],"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/naufalahnaf17.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":"2024-09-12T07:14:41.000Z","updated_at":"2024-09-25T17:38:16.000Z","dependencies_parsed_at":"2024-09-16T10:13:28.553Z","dependency_job_id":"f2622f9d-8783-4777-bd4e-68e8e1f82fcf","html_url":"https://github.com/naufalahnaf17/pytorch-cv-project","commit_stats":{"total_commits":29,"total_committers":2,"mean_commits":14.5,"dds":"0.13793103448275867","last_synced_commit":"f6377d275623c7b534c749dabb02effa095b7bdb"},"previous_names":["naufalahnaf17/pytorch-cv-project"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/naufalahnaf17%2Fpytorch-cv-project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/naufalahnaf17%2Fpytorch-cv-project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/naufalahnaf17%2Fpytorch-cv-project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/naufalahnaf17%2Fpytorch-cv-project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/naufalahnaf17","download_url":"https://codeload.github.com/naufalahnaf17/pytorch-cv-project/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250023553,"owners_count":21362421,"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":["beginner-project","computer-vision","fine-tuning","huggingface","onnxruntime","python","pytorch"],"created_at":"2024-10-01T17:02:15.030Z","updated_at":"2026-01-11T01:35:12.964Z","avatar_url":"https://github.com/naufalahnaf17.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Computer Vision Project\n\nThese are some mini projects I created using Pytorch for computer vision tasks\n\nin this repo I will create a mini project with various tasks in computer vision such as image classification, object detection, object segmentation, GAN and many more\n\nadd a star to get updates from this repo\n\n#### Repo Update\n- **26 Sep 2024 -\u003e inference next js plant-species-classification**\n- **25 Sep 2024 -\u003e inference next js cat-and-dogs-classification**\n- **20 Sep 2024 -\u003e facemask-detection**\n- **17 Sep 2024 -\u003e manga-text-detection**\n- **17 Sep 2024 -\u003e plant-species-classification**\n- **16 Sep 2024 -\u003e cat-and-dogs-classification**\n\n### Dont have CUDA for Training ? Download Model Here\n\n| Model Name         | Model URL                                                                |\n| ----------------- | ------------------------------------------------------------------ |\n| Cat and Dogs | [click here to download](https://drive.google.com/file/d/1Tfh30c0BShuSTTpvgeCYBHK2aZdkhjV0/view?usp=drive_link) |\n| Plant Species | [click here to download](https://drive.google.com/file/d/1OYLj2TIK2oTglLJMRt2t7BW2tGLM6178/view?usp=drive_link) |\n| Manga Text | [click here to download](https://drive.google.com/file/d/1kI_RXo2hoQ9fQWU3CcB1wrw3-CFOfKe4/view?usp=drive_link) |\n| Facemask Detection | [click here to download](https://drive.google.com/file/d/1J2AKUaLGDlDAXvZCgUNtsz-Hhyqw7EVv/view?usp=drive_link) |\n\n## cat-and-dogs-classification (Created : 16-09-2024)\n\nin this project, I focused on fine-tune the resnet-50 model then exported it to onnx format.\n\nwhich initially resnet-50 outputs approximately 1000 classes into just 2 classes according to the dataset that has been downloaded, namely cats and dogs\n\n- Loss : 0.06402150790199812\n- Accuracy : 98.46762234305487%\n- Epochs : 5\n\n![Pred_3](cat-and-dogs-classification/screenshot/save_3.PNG)\n\n## plant-species-classification (Created : 17-09-2024)\n\nin this project, I focused on fine-tune the google/vit-base-patch16-224 model then exported it to onnx format.\n\nwhich initially google/vit-base-patch16-224 outputs approximately 1000 classes into just 47 classes according to the dataset that has been downloaded, namely house-plant-species\n\n- Loss : 0.305279920695395\n- Accuracy : 93.55418434246046%\n- Epochs : 5\n\n![Pred_1](plant-species-classification/screenshot/save_1.JPG)\n\n## manga-text-detection (Created : 17-09-2024)\n\nin this project, I focused on fine-tune the faster-RCNN model then exported it to onnx format.\n\ncreate object detection on text in manga pages with the manga-text-detection dataset\n\n- Loss : 0.105800\n- Epochs : 25\n- MAP : 0.9\n- MAP-50 : 1.0\n- MAP-75 : 0.9901\n\n![Pred_1](manga-text-detection/screenshot/save_1.JPG)\n![Pred_2](manga-text-detection/screenshot/save_2.JPG)\n\n## facemask-detection (Created : 20-09-2024)\n\nin this project, I focused on fine-tune the YOLOv10 model then exported it to onnx format.\n\ncreate object detection on facemask-dataset\n\n- Loss : 0.405800\n- Epochs : 50\n- MAP : 0.908\n- MAP-50 : 0.934\n- MAP-75 : 0.666\n\n![Pred_1](facemask-detection/screenshot/save_1.JPG)\n![Pred_2](facemask-detection/screenshot/save_2.JPG)\n\n## Todo List \n- [x] Fine tune resnet-50 on the cats and dogs dataset\n  - [x] Create inference with opencv and onnxruntime (python)\n  - [x] Create inference with next.js and onnxruntime-web\n  - [ ] Create Inference with kotlin\n- [x] Fine tune vit-base-224 on the plant species dataset\n  - [x] Create inference with opencv and onnxruntime (python)\n  - [x] Create inference with next.js and onnxruntime-web\n  - [ ] Create Inference with kotlin\n- [x] Fine tune Faster-RCNN on the manga text detection dataset\n  - [x] Create inference with opencv and onnxruntime (python)\n  - [ ] Create inference with next.js and onnxruntime-web\n- [x] Fine tune YOLO-V10 on the facemask dataset\n  - [x] Create inference with opencv and onnxruntime (python)\n  - [ ] Create inference with next.js and onnxruntime-web\n  - [ ] Create Inference with kotlin and run with input uint8\n\n\n## Authors\n\n- [@naufalahnaf17](https://www.github.com/naufalahnaf17)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnaufalahnaf17%2Fpytorch-cv-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnaufalahnaf17%2Fpytorch-cv-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnaufalahnaf17%2Fpytorch-cv-project/lists"}