{"id":13644181,"url":"https://github.com/avanetten/yoltv5","last_synced_at":"2025-04-21T07:30:28.982Z","repository":{"id":39167056,"uuid":"455538808","full_name":"avanetten/yoltv5","owner":"avanetten","description":"YOLT, now with PyTorch.","archived":false,"fork":false,"pushed_at":"2023-02-09T07:33:53.000Z","size":1996,"stargazers_count":194,"open_issues_count":14,"forks_count":29,"subscribers_count":7,"default_branch":"main","last_synced_at":"2024-11-09T16:44:01.358Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/avanetten.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}},"created_at":"2022-02-04T12:26:42.000Z","updated_at":"2024-10-17T09:56:25.000Z","dependencies_parsed_at":"2024-01-14T12:18:19.219Z","dependency_job_id":"291bf9e4-bda9-45d0-97a6-d86b1b597782","html_url":"https://github.com/avanetten/yoltv5","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/avanetten%2Fyoltv5","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avanetten%2Fyoltv5/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avanetten%2Fyoltv5/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avanetten%2Fyoltv5/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/avanetten","download_url":"https://codeload.github.com/avanetten/yoltv5/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250014525,"owners_count":21360967,"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":"2024-08-02T01:01:58.661Z","updated_at":"2025-04-21T07:30:27.453Z","avatar_url":"https://github.com/avanetten.png","language":"Python","funding_links":[],"categories":["Object Detection Applications"],"sub_categories":[],"readme":"# YOLTv5 #\n\n![Alt text](/results/__examples/header.jpg?raw=true \"\")\n \n YOLTv5 rapidly detects objects in arbitrarily large aerial or satellite images that far exceed the ~600×600 pixel size typically ingested by deep learning object detection frameworks. \n  \n YOLTv5 builds upon [YOLT]( https://github.com/avanetten/yolt) and [SIMRDWN]( https://github.com/avanetten/simrdwn), and updates these frameworks to use the [YOLOv5](https://github.com/ultralytics/yolov5) version of the [YOLO](https://pjreddie.com/darknet/yolo/) object detection family.  This repository has generally similar performance to the [Darknet](https://pjreddie.com/darknet/)-based [YOLTv4](https://github.com/avanetten/yoltv4) repository.  For those users who prefer a [PyTorch](https://pytorch.org) backend, however, we provide YOLTv5.  \n \n Below, we provide examples of how to use this repository with the open-source [SpaceNet](https://spacenet.ai) dataset. \n \n____\n## Running YOLTv5\n\n___\n\n### 0. Installation (Preliminary)\n\nYOLTv5 is built to execute on a GPU-enabled machine. \n\n\tcd yoltv5/yolov5\n\tpip install -r requirements.txt \n\n\t# update with geo packages\n\tconda install -c conda-forge gdal\n\tconda install -c conda-forge osmnx=0.12 \n\tconda install  -c conda-forge scikit-image\n\tconda install  -c conda-forge statsmodels\n\tpip install torchsummary\n\tpip install utm\n\tpip install numba\n\tpip install jinja2==2.10\n\n___\n\n### 1. Train\n\nTraining preparation is accomplished via [prep_train.py](https://github.com/avanetten/yoltv5/blob/main/yoltv5/prep_train.py).  To train a model, run:\n\n\tcd /yoltv5\n    python yolov5/train.py --img 640 --batch 16 --epochs 100 --data yoltv5_train_vehicles_8cat.yaml --weights yolov5l.pt\n\n___\n\n### 2. Test\n\nSimply edit [yoltv5_test_vehicles_8cat.yaml](https://github.com/avanetten/yoltv5/blob/main/configs/yoltv5_test_vehicles_8cat.yaml) to point to the appropriate locations, then run the _test.sh_ script:\n\n\tcd yoltv5\n\t./test.sh ../configs/yoltv5_test_vehicles_8cat.yaml\n\n\nOutputs will look something like the figure below (cars=green, trucks=red, buses=blue):\n\n![Alt text](/results/__examples/khartoum_example0.jpg?raw=true \"\")\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favanetten%2Fyoltv5","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Favanetten%2Fyoltv5","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favanetten%2Fyoltv5/lists"}