{"id":20041691,"url":"https://github.com/ajithvcoder/deblurganv2_customdataset","last_synced_at":"2025-09-20T09:31:16.257Z","repository":{"id":162842244,"uuid":"637334808","full_name":"ajithvcoder/DeblurGANv2_Customdataset","owner":"ajithvcoder","description":"Using deblur GAN on custom dataset","archived":false,"fork":false,"pushed_at":"2023-05-07T10:40:03.000Z","size":17159,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-03T05:31:49.338Z","etag":null,"topics":["custom-dataset","deblurgan","deblurring","deep-learning","gan","generative-adversarial-network"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ajithvcoder.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}},"created_at":"2023-05-07T08:29:36.000Z","updated_at":"2024-08-02T06:13:17.000Z","dependencies_parsed_at":"2023-06-27T19:19:26.094Z","dependency_job_id":null,"html_url":"https://github.com/ajithvcoder/DeblurGANv2_Customdataset","commit_stats":{"total_commits":6,"total_committers":1,"mean_commits":6.0,"dds":0.0,"last_synced_commit":"ed75404de7700d3fb1f0e351e26e3c1b9b99f6cd"},"previous_names":["ajithvcoder/deblurganv2_customdataset"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ajithvcoder/DeblurGANv2_Customdataset","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajithvcoder%2FDeblurGANv2_Customdataset","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajithvcoder%2FDeblurGANv2_Customdataset/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajithvcoder%2FDeblurGANv2_Customdataset/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajithvcoder%2FDeblurGANv2_Customdataset/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ajithvcoder","download_url":"https://codeload.github.com/ajithvcoder/DeblurGANv2_Customdataset/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajithvcoder%2FDeblurGANv2_Customdataset/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":276076991,"owners_count":25581287,"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","status":"online","status_checked_at":"2025-09-20T02:00:10.207Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["custom-dataset","deblurgan","deblurring","deep-learning","gan","generative-adversarial-network"],"created_at":"2024-11-13T10:47:30.654Z","updated_at":"2025-09-20T09:31:15.209Z","avatar_url":"https://github.com/ajithvcoder.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Using deblurv2 GAN on custom dataset\n\n**Dataset preparation**\n\nYou can download any set of images which are text, scenery etc . Using gaussian blur you can blur a copy of the images.\nI have took  a dataset from [roboflow](https://universe.roboflow.com/yashwanthworkspace/numbers-identification) .\nMade following folders \n```\n--Licenseplate_blur_clear_dataset\n    --train\n        --blur\n        --sharp\n    --test\n        --blur\n        --sharp\n    --valid\n        --blur\n        --sharp\n```\nCopy original images of train,test,valid to sharp folder. To fill the images in blur folder you can use [this code](./util/blur_image.py). now we are done with data preparation. Dataset which i prepared can be [found here](https://drive.google.com/file/d/1Mk99lU3zJgBkBpHTl0PigJ3UiSX4yyKB/view?usp=sharing)\n\n**Installation**\n\n```pip install -r requirements.txt```\n\n**Train**\n\n```python train.py```\n\n**Test**\n\npretrained weights can be [found here](https://drive.google.com/file/d/1M0zk2udF6GfGgMI84xCcGrUmnyZGsg1T/view?usp=sharing)\n\n```python predict.py -i ./test_img -o ./submit -m ./saved_models/best_fpn.h5``` \n\n**Gallery**\n\n\u003cp float=\"left\"\u003e\n\u003cimg src=\"./assets/13.jpg\" alt=\"Number plate\" width=\"250\" height=\"250\"/\u003e\n\u003cimg src=\"./assets/13_deblur.jpg\" alt=\"Number plate\" width=\"250\" height=\"250\"/\u003e\n\u003c/p\u003e\n\n\u003cp float=\"left\"\u003e\n\u003cimg src=\"./assets/100.jpg\" alt=\"Number plate\" width=\"250\" height=\"250\"\u003e\n\u003cimg src=\"./assets/100_deblur.jpg\" alt=\"Number plate\" width=\"250\" height=\"250\"\u003e\n\u003c/p\u003e\n\n\u003cp float=\"left\"\u003e\n\u003cimg src=\"./assets/107.jpg\" alt=\"Number plate\" width=\"250\" height=\"250\"\u003e\n\u003cimg src=\"./assets/107_deblur.jpg\" alt=\"Number plate\" width=\"250\" height=\"250\"\u003e\n\u003c/p\u003e\n\n**Colab Notebook**\n\n[Notebook](https://colab.research.google.com/drive/1yHv9dZt_GYQW69RSbShhwR1TChauF9BL?usp=sharing)\n\n**Credits**\n\n- [DeblurGANv2](https://github.com/VITA-Group/DeblurGANv2)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fajithvcoder%2Fdeblurganv2_customdataset","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fajithvcoder%2Fdeblurganv2_customdataset","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fajithvcoder%2Fdeblurganv2_customdataset/lists"}