{"id":13643183,"url":"https://github.com/AlexeyAB/yolo2_light","last_synced_at":"2025-04-20T21:33:19.575Z","repository":{"id":70342148,"uuid":"97626494","full_name":"AlexeyAB/yolo2_light","owner":"AlexeyAB","description":"Light version of convolutional neural network Yolo v3 \u0026 v2 for objects detection with a minimum of dependencies (INT8-inference, BIT1-XNOR-inference)","archived":false,"fork":false,"pushed_at":"2019-08-29T10:00:48.000Z","size":2122,"stargazers_count":302,"open_issues_count":64,"forks_count":116,"subscribers_count":25,"default_branch":"master","last_synced_at":"2024-11-06T06:47:59.085Z","etag":null,"topics":["bit1-xnor-inference","computer-vision","machine-learning","neural-network","object-detection"],"latest_commit_sha":null,"homepage":"","language":"C","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AlexeyAB.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":"2017-07-18T17:37:43.000Z","updated_at":"2024-10-15T05:41:52.000Z","dependencies_parsed_at":"2023-02-22T04:15:20.934Z","dependency_job_id":null,"html_url":"https://github.com/AlexeyAB/yolo2_light","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexeyAB%2Fyolo2_light","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexeyAB%2Fyolo2_light/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexeyAB%2Fyolo2_light/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexeyAB%2Fyolo2_light/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AlexeyAB","download_url":"https://codeload.github.com/AlexeyAB/yolo2_light/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223839441,"owners_count":17211942,"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":["bit1-xnor-inference","computer-vision","machine-learning","neural-network","object-detection"],"created_at":"2024-08-02T01:01:43.296Z","updated_at":"2024-11-09T14:31:55.565Z","avatar_url":"https://github.com/AlexeyAB.png","language":"C","funding_links":[],"categories":["Lighter and Deployment Frameworks"],"sub_categories":[],"readme":"# yolo2_light\nLight version of convolutional neural network Yolo v3 \u0026 v2 for objects detection with a minimum of dependencies (INT8-inference, BIT1-XNOR-inference)\n\nThis repository supports:\n\n* both Windows and Linux\n* both OpenCV \u003c= 3.3.0 and OpenCV 2.4.13\n* both cuDNN \u003e= 7.1.1\n* CUDA \u003e= 8.0\n\nHow to compile:\n* To compile for CPU just do `make` on Linux or build `yolo_cpu.sln` on Windows\n* To compile for GPU set flag `GPU=1` in the `Makefile` on Linux or build `yolo_gpu.sln` on Windows\n    \n    Required both [CUDA \u003e= 8.0](https://developer.nvidia.com/cuda-toolkit-archive) and [cuDNN \u003e= 7.1.1](https://developer.nvidia.com/rdp/cudnn-archive)\n\nHow to start:\n* Download [`yolov3.weights`](https://pjreddie.com/media/files/yolov3.weights) to the `bin` directory and run `./yolo.sh` on Linux (or `yolo_cpu.cmd` / `yolo_gpu.cmd` on Windows)\n* Download [`yolov3-tiny.weights`](https://pjreddie.com/media/files/yolov3-tiny.weights) to the `bin` directory and run `./tiny-yolo.sh`\n\nHow to use **INT8**-inference:\n* Use flag `-quantized` at the end of command, for example, [`tiny-yolo-int8.sh`](https://github.com/AlexeyAB/yolo2_light/blob/master/bin/tiny-yolo-int8.sh) or [`yolo_cpu_int8.cmd`](https://github.com/AlexeyAB/yolo2_light/blob/master/bin/yolo_cpu_int8.cmd)\n* For the custom dataset, you should use `input_calibration=` parameter in your cfg-file, from the correspon cfg-file: [`yolov3-tiny.cfg`](https://github.com/AlexeyAB/yolo2_light/blob/29905072f194ee86fdeed6ff2d12fed818712411/bin/yolov3-tiny.cfg#L25) or [`yolov3.cfg`](https://github.com/AlexeyAB/yolo2_light/blob/29905072f194ee86fdeed6ff2d12fed818712411/bin/yolov3.cfg#L25), ...\n\nHow to use **BIT1-XNOR**-inference - only for custom models (you should train it by yourself):\n* You should base your cfg-file on [`yolov3-spp_xnor_obj.cfg`](https://github.com/AlexeyAB/darknet/files/2853459/yolov3-spp_xnor_obj.cfg.txt) and train it by using this repository as usual https://github.com/AlexeyAB/darknet by using pre-trained file [`darknet53_448_xnor.conv.74`](https://drive.google.com/open?id=1IT-vvyxRLlxY5g9rJp_G2U3TXYphjBv8)\n* Then use it for Detection-test or for getting Accuracy (mAP):\n    * `./darknet detector test data/obj.names yolov3-spp_xnor_obj.cfg data/yolov3-spp_xnor_obj_5000.weights -thresh 0.15 dog.jpg`\n\t* `./darknet detector map data/obj.data yolov3-spp_xnor_obj.cfg data/yolov3-spp_xnor_obj_5000.weights -thresh 0.15`\n\nOther models by the link: https://pjreddie.com/darknet/yolo/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAlexeyAB%2Fyolo2_light","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FAlexeyAB%2Fyolo2_light","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAlexeyAB%2Fyolo2_light/lists"}