{"id":18494203,"url":"https://github.com/rajdeep2804/darknet_yolo_tutorial","last_synced_at":"2025-08-16T07:14:16.675Z","repository":{"id":229294991,"uuid":"437078871","full_name":"rajdeep2804/Darknet_yolo_tutorial","owner":"rajdeep2804","description":"This repo acts like a training guide for yolo object detection model for custom data.","archived":false,"fork":false,"pushed_at":"2021-12-10T18:39:47.000Z","size":9417,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-14T03:00:04.037Z","etag":null,"topics":["darknet","object-detection","training","tutorial","yolo","yolov3"],"latest_commit_sha":null,"homepage":"","language":"C","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/rajdeep2804.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}},"created_at":"2021-12-10T18:34:41.000Z","updated_at":"2022-03-23T11:41:39.000Z","dependencies_parsed_at":"2024-03-23T12:22:28.622Z","dependency_job_id":null,"html_url":"https://github.com/rajdeep2804/Darknet_yolo_tutorial","commit_stats":null,"previous_names":["rajdeep2804/darknet_yolo_tutorial"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/rajdeep2804/Darknet_yolo_tutorial","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajdeep2804%2FDarknet_yolo_tutorial","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajdeep2804%2FDarknet_yolo_tutorial/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajdeep2804%2FDarknet_yolo_tutorial/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajdeep2804%2FDarknet_yolo_tutorial/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rajdeep2804","download_url":"https://codeload.github.com/rajdeep2804/Darknet_yolo_tutorial/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajdeep2804%2FDarknet_yolo_tutorial/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270680054,"owners_count":24627116,"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":"2025-08-16T02:00:11.002Z","response_time":91,"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":["darknet","object-detection","training","tutorial","yolo","yolov3"],"created_at":"2024-11-06T13:18:22.171Z","updated_at":"2025-08-16T07:14:16.643Z","avatar_url":"https://github.com/rajdeep2804.png","language":"C","readme":"# Darknet_yolo_tutorial\n\n# Training Framework\n\nA generalised training framework consisting of all kinds of models like Yolo, RCNN etc. with default model configurations.\n\n## Description\nThis repo acts like a training guide for yolo object detection model got custom data.\n\n## Testing CUDA,\nTo test that CUDA works, go to the CUDA demo suite directory:\n`cd /usr/local/cuda/extras/demo_suite/`\n./deviceQuery\n\n## Executing  darknet\nDownload the yolov3 weights in Darknet dir:\n`wget https://pjreddie.com/media/files/yolov3.weights`\n\nMake Sure in `Makefile` 'gpu == 1'.\nFrom darknet dir run `make`\n\nFor Testing Darknet:\n./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg\n\n###  Custom Training,\nCopy \"yolov3.cfg\" file from cfg to custom_data/cfg dir, and rename to `yolov3-custom.cfg`\n\n## Making changes in yolov3-custom.cfg file:\n\nThe maximum number of iterations for which our network should be trained is set with the param `max_batches=4000`. Also update `steps=3200,3600` which is 80%, 90% of max_batches, you can set value based on your training requirements.\n\nclasses param in the yolo layers to based on number of classes you are workning with like for one or `2 class` at `line numbers: 610, 696, 783`.\n\nSimilarly we will need to update the filters param based on the classes count `filters=(classes + 5) * 3`. \nFor a single class we should set `filters=18` at `line numbers: 603, 689, 776`.\n\n## Updating custom_data dir,\n### Updating \"custom.names\" file : Mention all class name,\n### Updating \"detector.names\" file : \n`classes=1`\ntrain=custom_data/train.txt //Path to text file of images path for training.\nvalid=custom_data/test.txt // Path to text file of images path for testing.\nnames=custom_data/custom.names //Path to the class names\nbackup=backup/ //path to save weights\n\n`Test.txt` need to store the path of each image used for testing\n`Train.txt`  need to store the path of each image used for training\n\n## Command to initialise training, \n```bash\n./darknet detector detector train custom_data/detector.data custom_data/cfg/yolov3-custom.cfg yolov3.weights\n```\n## Evaluating your training,\n```bash \n./darknet detector test custom_data/detector.data custom_data/cfg/yolov3-custom.cfg backup/yolov3_final.weights -ext_output -out eval.json \u003c eval.txt\n./darknet detector map data/obj.data custom_data/cfg/yolov3-custom.cfg backup/yolov3_final.weights\n./darknet detector recall data/obj.data custom_data/cfg/yolov3-custom.cfg backup/yolov3_final.weights\n```\n#note eval.json will store all the output bounding box for each input image path stored in the eval.txt, //eval.txt will be prepared exactly like `test.txt/train.txt`","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frajdeep2804%2Fdarknet_yolo_tutorial","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frajdeep2804%2Fdarknet_yolo_tutorial","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frajdeep2804%2Fdarknet_yolo_tutorial/lists"}